From fe3278e7ab80b6cc58bc15cd69344f6f3bed274a Mon Sep 17 00:00:00 2001 From: Vadym Samoilenko Date: Mon, 18 May 2026 19:41:01 +0100 Subject: [PATCH] vault backup: 2026-05-18 19:41:01 --- .../hp-prod-tracker/DEVELOPER_MANUAL.md | 23 ++- 01 Projects/hp-prod-tracker/USER_MANUAL.md | 17 +- .../loreal-sla-calculator/DEVELOPER_MANUAL.md | 18 +- .../loreal-sla-calculator/USER_MANUAL.md | 16 +- .../loreal-timelog-viewer/DEVELOPER_MANUAL.md | 9 + .../loreal-timelog-viewer/USER_MANUAL.md | 9 + 01 Projects/md to word/DEVELOPER_MANUAL.md | 12 +- 01 Projects/md to word/USER_MANUAL.md | 13 ++ 01 Projects/semblance/DEVELOPER_MANUAL.md | 28 ++- 01 Projects/semblance/USER_MANUAL.md | 16 +- .../DEVELOPER_MANUAL.md | 26 ++- .../video-accessibility-old/USER_MANUAL.md | 16 +- 05 Aimpress LTD/Shumiland/Shumiland.md | 45 ++++- 4a5c465b25cfe73154c51bd2bc8758a6_MD5.svg | 1 + 799a7f85a6cd2ee30f64fd9d7763519e_MD5.png | Bin 0 -> 12333 bytes 8411fb34fe3c1ed62e71648aed13c84b_MD5.svg | 1 + 8a4d52b2d756a11b786a67d977590d8e_MD5.svg | 1 + a1e5e56cbdcc97300e3228bc0aabc119_MD5.svg | 1 + f5fcdb3f89064840ca4ee81433cc5e03_MD5.svg | 1 + raw/_processed/nousresearch-hermes-agent.md | 178 ++++++++++++++++++ wiki/_master-index.md | 3 +- wiki/ai-agents/_index.md | 17 ++ wiki/ai-agents/hermes-agent.md | 157 +++++++++++++++ 23 files changed, 589 insertions(+), 19 deletions(-) create mode 100644 4a5c465b25cfe73154c51bd2bc8758a6_MD5.svg create mode 100644 799a7f85a6cd2ee30f64fd9d7763519e_MD5.png create mode 100644 8411fb34fe3c1ed62e71648aed13c84b_MD5.svg create mode 100644 8a4d52b2d756a11b786a67d977590d8e_MD5.svg create mode 100644 a1e5e56cbdcc97300e3228bc0aabc119_MD5.svg create mode 100644 f5fcdb3f89064840ca4ee81433cc5e03_MD5.svg create mode 100644 raw/_processed/nousresearch-hermes-agent.md create mode 100644 wiki/ai-agents/_index.md create mode 100644 wiki/ai-agents/hermes-agent.md diff --git a/01 Projects/hp-prod-tracker/DEVELOPER_MANUAL.md b/01 Projects/hp-prod-tracker/DEVELOPER_MANUAL.md index 13c4bf5..121d412 100644 --- a/01 Projects/hp-prod-tracker/DEVELOPER_MANUAL.md +++ b/01 Projects/hp-prod-tracker/DEVELOPER_MANUAL.md @@ -1,7 +1,23 @@ --- auto_generated: true +created: 2026-05-18 manual_updated_at: 2026-05-18 modified: 2026-05-18 +name: Developer_Manual +status: active +tags: +- client/oliver +- tech/azure-ad +- tech/claude +- tech/docker +- tech/nextjs +- tech/ollama +- tech/pgvector +- tech/postgresql +- tech/react +- tech/tailwind +- tech/typescript +type: project --- # HP CG Production Tracker - Developer Manual @@ -169,4 +185,9 @@ The `docker-compose.yml` defines: 2. **AI Fallback:** If `ANTHROPIC_API_KEY` is not set, the app falls back to Ollama. Ensure Ollama is running and the model `gemma4` or `qwen3` is pulled. 3. **PKCE Flow:** Since this is an SPA, do not use `AZURE_CLIENT_SECRET`. Ensure the Azure App Registration is set up as a "Single Page Application" with PKCE. 4. **Vector Search:** Ensure `pgvector` is enabled in PostgreSQL. The Docker volume `./docker/db-init.sql` handles this, but verify it runs on DB restart. -5. **File Uploads:** Media uploads are stored in `uploads_data` volume. Ensure the Docker user has write permissions to `/data/uploads`. \ No newline at end of file +5. **File Uploads:** Media uploads are stored in `uploads_data` volume. Ensure the Docker user has write permissions to `/data/uploads`. + +## Related +- [[01 Projects/ppt-tool/DEVELOPER_MANUAL.md]] +- [[01 Projects/olivas/DEVELOPER_MANUAL.md]] +- [[01 Projects/Oliver-ai-bot_2.0/DEVELOPER_MANUAL.md]] \ No newline at end of file diff --git a/01 Projects/hp-prod-tracker/USER_MANUAL.md b/01 Projects/hp-prod-tracker/USER_MANUAL.md index 28f8c20..e80a9b6 100644 --- a/01 Projects/hp-prod-tracker/USER_MANUAL.md +++ b/01 Projects/hp-prod-tracker/USER_MANUAL.md @@ -1,7 +1,19 @@ --- auto_generated: true +created: 2026-05-18 manual_updated_at: 2026-05-18 modified: 2026-05-18 +name: User_Manual +status: active +tags: +- domain/analytics +- tech/azure-ad +- tech/claude +- tech/node +- tech/react +- tech/typescript +- type/sop +type: sop --- # HP CG Production Tracker - User Manual @@ -109,4 +121,7 @@ A: Ensure you have selected the correct project context. If no projects are visi A: Yes. The application supports video uploads processed by FFmpeg. You can view previews via HLS.js in the deliverable details. **Q: Is the AI assistant free?** -A: The AI assistant uses local inference via Ollama for embeddings and fallbacks, and Claude API for primary queries. Availability depends on server configuration and API limits set by the admin. \ No newline at end of file +A: The AI assistant uses local inference via Ollama for embeddings and fallbacks, and Claude API for primary queries. Availability depends on server configuration and API limits set by the admin. + +## Related +- [[01 Projects/cc-dashboard/USER_MANUAL.md]] \ No newline at end of file diff --git a/01 Projects/loreal-sla-calculator/DEVELOPER_MANUAL.md b/01 Projects/loreal-sla-calculator/DEVELOPER_MANUAL.md index fe7f871..b7cf293 100644 --- a/01 Projects/loreal-sla-calculator/DEVELOPER_MANUAL.md +++ b/01 Projects/loreal-sla-calculator/DEVELOPER_MANUAL.md @@ -1,7 +1,20 @@ --- auto_generated: true +created: 2026-05-18 manual_updated_at: 2026-05-18 modified: 2026-05-18 +name: Developer_Manual +status: active +tags: +- client/loreal +- domain/analytics +- domain/security +- tech/azure-ad +- tech/docker +- tech/node +- tech/postgresql +- type/sop +type: sop --- # L'Oréal SLA Calculator Developer Manual @@ -95,4 +108,7 @@ The application is a hybrid architecture: - **Auth Bypass**: Authentication is explicitly bypassed on `localhost` and `127.0.0.1` for development convenience. - **Token Refresh**: The frontend attempts one silent token refresh on 401 errors before logging the user out. - **Config Caching**: Browsers may aggressively cache `config.json`. Use the timestamp query string (`?v=...`) to force updates during development. -- **Password Encoding**: Passwords are Base64 encoded before transmission in the legacy email/password flow to avoid WAF issues with special characters. \ No newline at end of file +- **Password Encoding**: Passwords are Base64 encoded before transmission in the legacy email/password flow to avoid WAF issues with special characters. + +## Related +- [[01 Projects/olivas/DEVELOPER_MANUAL.md]] \ No newline at end of file diff --git a/01 Projects/loreal-sla-calculator/USER_MANUAL.md b/01 Projects/loreal-sla-calculator/USER_MANUAL.md index 27c2a10..9025cf8 100644 --- a/01 Projects/loreal-sla-calculator/USER_MANUAL.md +++ b/01 Projects/loreal-sla-calculator/USER_MANUAL.md @@ -1,7 +1,18 @@ --- auto_generated: true +created: 2026-05-18 manual_updated_at: 2026-05-18 modified: 2026-05-18 +name: User_Manual +status: active +tags: +- client/loreal +- status/active +- tech/nextjs +- tech/python +- tech/react +- type/sop +type: sop --- # L'Oréal SLA Calculator User Manual @@ -59,4 +70,7 @@ A: Yes, revision rounds can be set with decimal precision in the PM Calculator c A: Non-developers can update assumptions, stage definitions, and default values by editing the `config.json` file directly. **Q: What happens if the deadline cannot be met?** -A: The tool provides a "No" verdict and allows you to adjust inputs (like complexity or revisions) to see how changes impact the timeline. \ No newline at end of file +A: The tool provides a "No" verdict and allows you to adjust inputs (like complexity or revisions) to see how changes impact the timeline. + +## Related +- [[01 Projects/lusa-back-planner/USER_MANUAL.md]] \ No newline at end of file diff --git a/01 Projects/loreal-timelog-viewer/DEVELOPER_MANUAL.md b/01 Projects/loreal-timelog-viewer/DEVELOPER_MANUAL.md index fda54dc..3bf739e 100644 --- a/01 Projects/loreal-timelog-viewer/DEVELOPER_MANUAL.md +++ b/01 Projects/loreal-timelog-viewer/DEVELOPER_MANUAL.md @@ -1,7 +1,16 @@ --- auto_generated: true +created: 2026-05-18 manual_updated_at: 2026-05-18 modified: 2026-05-18 +name: Developer_Manual +status: active +tags: +- client/loreal +- domain/devops +- tech/react +- type/reference +type: reference --- # Loreal Timelog Viewer Developer Manual diff --git a/01 Projects/loreal-timelog-viewer/USER_MANUAL.md b/01 Projects/loreal-timelog-viewer/USER_MANUAL.md index 22b59e0..a7961a1 100644 --- a/01 Projects/loreal-timelog-viewer/USER_MANUAL.md +++ b/01 Projects/loreal-timelog-viewer/USER_MANUAL.md @@ -1,7 +1,16 @@ --- auto_generated: true +created: 2026-05-18 manual_updated_at: 2026-05-18 modified: 2026-05-18 +name: User_Manual +status: active +tags: +- client/loreal +- domain/analytics +- status/active +- type/sop +type: sop --- # Loreal Timelog Viewer User Manual diff --git a/01 Projects/md to word/DEVELOPER_MANUAL.md b/01 Projects/md to word/DEVELOPER_MANUAL.md index 07192bc..2700c2d 100644 --- a/01 Projects/md to word/DEVELOPER_MANUAL.md +++ b/01 Projects/md to word/DEVELOPER_MANUAL.md @@ -1,7 +1,17 @@ --- auto_generated: true +created: 2026-05-18 manual_updated_at: 2026-05-18 modified: 2026-05-18 +name: Developer_Manual +status: active +tags: +- domain/devops +- tech/docker +- tech/hatchling +- tech/python +- type/sop +type: sop --- # MD to Word Converter Developer Manual @@ -115,4 +125,4 @@ A Dockerfile can be created to containerize the application. Ensure system depen - **Font Loading**: Mermaid CSS loads Montserrat from Google Fonts. In offline environments, provide a local font file or use a different font family. - **Temporary Files**: The tool creates temp files for Mermaid rendering. These are not cleaned up automatically in all cases. - **Python Version**: Requires Python 3.9+. Do not use with Python <3.9 due to dependency compatibility. -- **Large Documents**: Performance may degrade with very large Markdown files due to repeated temp file creation and Mermaid rendering. +- **Large Documents**: Performance may degrade with very large Markdown files due to repeated temp file creation and Mermaid rendering. \ No newline at end of file diff --git a/01 Projects/md to word/USER_MANUAL.md b/01 Projects/md to word/USER_MANUAL.md index ff15718..31e11e0 100644 --- a/01 Projects/md to word/USER_MANUAL.md +++ b/01 Projects/md to word/USER_MANUAL.md @@ -1,7 +1,16 @@ --- auto_generated: true +created: 2026-05-18 manual_updated_at: 2026-05-18 modified: 2026-05-18 +name: User_Manual +status: active +tags: +- domain/devops +- tech/markdown +- tech/python +- type/sop +type: sop --- # MD to Word Converter User Manual @@ -97,3 +106,7 @@ A: The current CLI supports one input file per run. Use shell loops or scripts t **Q: What happens if a Mermaid diagram has syntax errors?** A: The renderer may fail silently or produce broken images. Check your Mermaid syntax carefully before conversion. + +## Related +- [[01 Projects/md to word/DEVELOPER_MANUAL.md]] +- [[Mermaid CLI Installation]] \ No newline at end of file diff --git a/01 Projects/semblance/DEVELOPER_MANUAL.md b/01 Projects/semblance/DEVELOPER_MANUAL.md index 159f5a2..298b1e2 100644 --- a/01 Projects/semblance/DEVELOPER_MANUAL.md +++ b/01 Projects/semblance/DEVELOPER_MANUAL.md @@ -1,7 +1,30 @@ --- auto_generated: true +created: 2026-05-18 manual_updated_at: 2026-05-18 modified: 2026-05-18 +name: Developer_Manual +status: active +tags: +- domain/ai +- domain/security +- tech/azure-ad +- tech/docker +- tech/express +- tech/gemini +- tech/jwt +- tech/mongodb +- tech/msal +- tech/node +- tech/react +- tech/reactive +- tech/socket-io +- tech/socket.io-client +- tech/sonner +- tech/tanstack-query +- tech/typescript +- type/sop +type: sop --- # Semblance Synthetic Society — Developer Manual @@ -177,4 +200,7 @@ Semblance is a full-stack web application with a React frontend and a Node.js ba The `parseMentions` function uses a specific regex for `@mentions`. Be aware that complex names with special characters or punctuation may not be parsed correctly. The regex stops at conjunctions (`and`, `or`) and non-word boundaries. 5. **Port Binding:** - Backend and MongoDB are bound to `127.0.0.1` in `docker-compose.yml`. This ensures they are not exposed to the public internet, but requires port forwarding or a reverse proxy for remote access. \ No newline at end of file + Backend and MongoDB are bound to `127.0.0.1` in `docker-compose.yml`. This ensures they are not exposed to the public internet, but requires port forwarding or a reverse proxy for remote access. + +## Related +- [[01 Projects/sandbox-notebookllamalm-nextjs/DEVELOPER_MANUAL.md]] \ No newline at end of file diff --git a/01 Projects/semblance/USER_MANUAL.md b/01 Projects/semblance/USER_MANUAL.md index 2320596..63346fc 100644 --- a/01 Projects/semblance/USER_MANUAL.md +++ b/01 Projects/semblance/USER_MANUAL.md @@ -1,7 +1,17 @@ --- auto_generated: true +created: 2026-05-18 manual_updated_at: 2026-05-18 modified: 2026-05-18 +name: User_Manual +status: active +tags: +- domain/ai +- tech/azure-ad +- tech/gemini +- tech/typescript +- type/sop +type: sop --- # Semblance Synthetic Society — User Manual @@ -97,4 +107,8 @@ A: Yes. Even in Autonomous Mode, if you have moderator privileges, you can type A: Persona data, session transcripts, and analytics are stored in the MongoDB database. Ensure you comply with your organization's data privacy policies when creating personas. **Q: How do I export session insights?** -A: Session summaries and theme extractions are available post-session. You can often export these as reports or view them in the analytics dashboard. \ No newline at end of file +A: Session summaries and theme extractions are available post-session. You can often export these as reports or view them in the analytics dashboard. + +## Related +- [[02 Areas/Market Research Processes]] +- [[03 Resources/AI Persona Design Guide]] \ No newline at end of file diff --git a/01 Projects/video-accessibility-old/DEVELOPER_MANUAL.md b/01 Projects/video-accessibility-old/DEVELOPER_MANUAL.md index 579d052..9686882 100644 --- a/01 Projects/video-accessibility-old/DEVELOPER_MANUAL.md +++ b/01 Projects/video-accessibility-old/DEVELOPER_MANUAL.md @@ -1,7 +1,26 @@ --- auto_generated: true +created: 2026-05-18 manual_updated_at: 2026-05-18 modified: 2026-05-18 +name: Developer_Manual +status: active +tags: +- client/oliver +- domain/accessibility +- domain/ai +- tech/azure-ad +- tech/celery +- tech/docker +- tech/fastapi +- tech/gemini +- tech/mongodb +- tech/python +- tech/react +- tech/redis +- tech/typescript +- type/sop +type: sop --- # Developer Manual: Accessible Video Processing Platform @@ -173,4 +192,9 @@ celery -A celery_app worker -Q whisper -c 1 2. **TTS Quotas**: Google Cloud TTS and ElevenLabs have rate limits. Monitor usage and implement backoff strategies in the TTS worker. 3. **WebSocket Reconnects**: The frontend handles auto-reconnects. Ensure the backend WebSocket server is stable; unexpected disconnections may require a manual page refresh if reconnect fails. 4. **Signed URLs**: Generated download links expire after 24 hours. If a user tries to download later, they must re-request the link from the API. -5. **MSAL Config**: Ensure `msalConfig.ts` matches the Azure AD redirect URIs exactly, including the `basename` (`/video-accessibility`) if deployed to a sub-path. \ No newline at end of file +5. **MSAL Config**: Ensure `msalConfig.ts` matches the Azure AD redirect URIs exactly, including the `basename` (`/video-accessibility`) if deployed to a sub-path. + +## Related +- [[01 Projects/oliver-ai-assistant/DEVELOPER_MANUAL.md]] +- [[01 Projects/ppt-tool/DEVELOPER_MANUAL.md]] +- [[01 Projects/ac-helper/DEVELOPER_MANUAL.md]] \ No newline at end of file diff --git a/01 Projects/video-accessibility-old/USER_MANUAL.md b/01 Projects/video-accessibility-old/USER_MANUAL.md index 7644008..706c6a9 100644 --- a/01 Projects/video-accessibility-old/USER_MANUAL.md +++ b/01 Projects/video-accessibility-old/USER_MANUAL.md @@ -1,7 +1,18 @@ --- auto_generated: true +created: 2026-05-18 manual_updated_at: 2026-05-18 modified: 2026-05-18 +name: User_Manual +status: active +tags: +- domain/accessibility +- domain/ai +- tech/docker +- tech/gemini +- tech/react +- type/sop +type: sop --- # User Manual: Accessible Video Processing Platform @@ -104,4 +115,7 @@ A: Check the **Job Detail** logs. If it remains stuck for more than 10 minutes, A: Files are stored in Google Cloud Storage with signed URLs that expire after 24 hours. The platform also enforces strict Role-Based Access Control (RBAC). **Q: Who can approve my work?** -A: Only users with the **Reviewer** or **Admin** role can approve jobs. Clients cannot self-approve their own submissions. \ No newline at end of file +A: Only users with the **Reviewer** or **Admin** role can approve jobs. Clients cannot self-approve their own submissions. + +## Related +- [[01 Projects/video-accessibility-old/DEVELOPER_MANUAL.md]] \ No newline at end of file diff --git a/05 Aimpress LTD/Shumiland/Shumiland.md b/05 Aimpress LTD/Shumiland/Shumiland.md index 671ce96..4f263a7 100644 --- a/05 Aimpress LTD/Shumiland/Shumiland.md +++ b/05 Aimpress LTD/Shumiland/Shumiland.md @@ -1,17 +1,41 @@ --- -name: "Shumiland" client: Aimpress LTD -status: active -server: aimpress -tech: [Next.js 16, Payload CMS 3, PostgreSQL 16, Docker, Traefik] -local_path: /Users/ai_leed/Documents/Projects/Shumiland -repo: https://git.ai-impress.com/Aimpress/Shumiland.git # Forgejo -deploy: "ssh aimpress → /opt/03-business/shumiland → git pull + docker compose build + up" -url: https://shumi.ai-impress.com -tags: [shumiland, nextjs, payload-cms, docker, ukraine, children-park] created: 2026-05-13 +deploy: ssh aimpress → /opt/03-business/shumiland → git pull + docker compose build + + up last_commit: 2026-05-13 +local_path: /Users/ai_leed/Documents/Projects/Shumiland +modified: 2026-05-18 +name: Shumiland port: 3000 +repo: https://git.ai-impress.com/Aimpress/Shumiland.git +server: aimpress +status: active +tags: +- children-park +- client/aimpress +- docker +- domain/devops +- nextjs +- payload-cms +- shumiland +- tech/docker +- tech/nextjs +- tech/payload-cms +- tech/postgresql +- tech/react +- tech/tailwind +- tech/typescript +- type/project +- ukraine +tech: +- Next.js 16 +- Payload CMS 3 +- PostgreSQL 16 +- Docker +- Traefik +type: project +url: https://shumi.ai-impress.com --- # Shumiland — Сайт дитячого парку @@ -224,3 +248,6 @@ pnpm payload migrate | 2026-05-13 | Nav dropdown hover fix (pt-2 bridge); "Детальніше" button on lokatsii page; dyvolis href fixes | | 2026-05-13 | DyvoLis: "Диво Ліс 250 грн" перший квиток; графік "щодня з 11:00 до 20:00" | | 2026-05-13 | DyvoLis visual overhaul: bg #f1fbeb, 3D coverflow gallery, WhyParents-style section, compact tickets | + +## Related +- [[05 Aimpress LTD/Shumiland/Shumiland.md]] \ No newline at end of file diff --git a/4a5c465b25cfe73154c51bd2bc8758a6_MD5.svg b/4a5c465b25cfe73154c51bd2bc8758a6_MD5.svg new file mode 100644 index 0000000..0a2c371 --- /dev/null +++ b/4a5c465b25cfe73154c51bd2bc8758a6_MD5.svg @@ -0,0 +1 @@ +LICENSE: MITLICENSEMIT \ No newline at end of file diff --git a/799a7f85a6cd2ee30f64fd9d7763519e_MD5.png b/799a7f85a6cd2ee30f64fd9d7763519e_MD5.png new file mode 100644 index 0000000000000000000000000000000000000000..2c4a160ceb721402e21ae107cbea45bbd80702b5 GIT binary patch literal 12333 zcmY*fby!qi69z;&7AcVyC8VUJT|!y}X_juJYw4wxl9rT4x&)*fK}rzmF6r)A>bqe4 z`2N{vpL5ThGk4CMdFP!uf%2~;urVHBARr)MOG&;^KtMot0sgn5ApyUBgl60b2p|Nh z7s5);h#M2=iDX7eJG;s8TT&gmB9cfV1Zd5~-eix879Msi*09!fGY6si)KbhYf6esM z47c$^XkeTzn%$Bx5+iPj0I{e;RTm|Zem)Mz1bui!Mvdw%757x)$HDUC+CzMFW=pbw)G%7EI-#=0y z-J)o}Cy{rM&{ha$NB=$$x{tU7(Hk5^y^-JzN4GJ)7Uk`X_H-mjA}QeBU&&9Ey{bS$ zsWk}pg=;JV!GEOQh}k80`q*pp(}W|Hm%7J*aTWt|IvP0p@zRZgMict2#!vKM4|%{ zQXyWysDJOJkTWoQZgUj>k5SVJXDxu2gc1QmwdF!ugZ}M}ZX`kp)$HR`i=y(w+|7yP z7{~+CIwa-2@ffM5ZG<3?qTKSNA;7x19 z+8W;({F!B z54%IwZGjH*v&ti)FC7_F6uVFgt?_6>@}K9G$u`txnfpo^Xr-3^tXGU zQE1z)g@)V?)V-dp#C1_|e;o;gLW+yvvv zD>?o)>}!+Dxu_ahtoPS$WcXu>1d0!f!i#!b#h2}ISjjMM%bf;Di$H(IE{)+VI zo}{cGz`(nY!qcX1i^eYWT#s9Dz0@Q6-rJA+Ut=h~1`$517CcMRieK7f78G=Q_Ec{( zv76D%)=j2TPq<4o$zH6Svvv`etc=FJAwl#x3}@NH>2uX4PwZG_rNg3uO3w$svo=P? zAgG3niE3U$N}bIt*%jcd(GTc7oYmBRMSbOWWzyd?!N<~&yV#N{Fvm@L=@_!o z=^)XrH7Ufr$1#aq1E61q>@1dQ@jX_h68Fg;S>=+%eiv!f%gJwzWY` z(8ivf#`2PV>x{<@En9AbokP|HSFZ(*k`!%w1fqy7Z4l1(E%TTEz+Zl0*GnM+JfLZ9 zIur|~X!*5D>QEeB<{#c5?3De!%ztM=>gORgpQzmtC|Q8Fh}@}{qUFb{Ky#wr8dHeV z5$Mv=66V`02^^3yK|houY`*#p3X!kA4k!h0rnabG8qTCDe&3=_G|-+&<&doPmq#Yq zF9s*^Dyvtzp%rqPU()7wy`I1NFeOS)rZCFAQjk0)Dmjxn&^ijO^|yHj^YtJsbwgVv zJ+SW@74$2!vOIk{-XLtE>xi2cKs`S#W`ec1?ubhb^KFO(hP?9Xt@~VF`Yu5nWs>J$ zzTH6=b_du;M2v!fj=|qPAAaB*ETq?Voxco+dsJ@#8@o}jl1!-*%8Na3Zu zBt5WZLvAVJUyuk_LEIBZ@IC>MDM+U$;QoK%&f68!#={c`{g>hv-v2`Ub&x|Q)GZ=Z zdTHhM|LEobfS$BOQs+HHZp7sO(5;WANmC|_Q9|rG-l5SoY5xYCM`A#DRCppq@dtlW zMZF9j0@C$>X!(9gg(pgn%C1b_g~eIH z`=>Ir4l>%!B|4nW3`due0 z-Fyj}1=O%!B5Oj3g_lZ8Uyo*k{OvRr%&{>Lct+nWX8LB_C6 zP{!^qKLoXsU`xA7u}+3>q)p}w=jRo#lvJl6u3hV!vmkHSTAL`uiOb!xclM6l{Vh#m z)=t(5$By0?p?p&q3eWF_(O9^sK9S5#62xo`Mg!2f$@~`L69I_70gogHtSX<6F!2X` zydc1~n+fth_+#uGyjl8d#GkxIx_Y118+^NgJJ4H%Wg)5@0FF}iE&dz6es+Snl5Bn| z(M0s$a@R8UfUMzhahBl%b5s7UCoiZ0%*8P3z4o*!%pHtBD?d^Myo7ySTIKgtKSJH# zj==@s;vml&PuC#2*1&h|Z|)CM-tt;C4&MH!%EyYPsf-wKC_VrKMJ#qYF+NS`Jx6UXrmHX&y$vH>I!6&2jiguP+)ZXiWC>>GNFCPs9hT^@qtsdn;x_&D%*i}wuoz=(kb87 zcXXM?EQp>Kay+RyCD3Z5295p5VtpnV%rX9;UF2Q0N}&RDY-`Qa3V=@PcdS1IQW*V6 z+z?+BpT@>;uqto&P2p3$%lnuNb8%6!x3XT1cy2Ld|JGwK(M-5&nSw7_ZG-1Z0`e|# z-2626s&kdXVt+fp`)ib^+3+SPSa_Xu0qRtd2vt92mhpI5;nd-==r|qi+uafe(~yyf z-O!s7D!SUGBF8aeki0ytT~64avLbnLaPH$t?oja#k%mFB;>;60$NdGB_bdC$g1y&* z>%%cqlxq)$y!E5ToEH-&V~d{16&BEYU%Gq7N=JS4V9(j(kV|!T=f3ROTk0*+_4{7# z<04jfSTj=Et-2UfsBny#{|>oTPHsMXl&#^y?_M?$4w5ia4IT6zn{iB|uCm#txw_8> zJx;?JsOM_^fh(tH7*$m9Nr{N2s{uHzB*muQh91WvijJegx9ToepWF&>^6*7wr-vxp zX?~1}&KIjs=GxtBq;~693FX!!Q-{gloj=H&mm2C!nR$-w^B643u+~pwDj%!s7+GYR z(1w(ce`~e;%%Ehiy2=AlZ9RYC?xlWVHf$)R<1Ke|h@Eg=JK0TI${2JUo;pB1b09++ zK-t$?&bx(=2uF`Mk3RUWm6p<16cRU>yGi%K6IWxy^an?tbstd~WfJ&cfZO!r!E^Wp z<%M5Gc-(g$iPu9*K{a40aGDm=Onc|AS_=7bIr^EMr44GOY3>yi5pdeamt*_-!<8MG zon>39Fb1!;v6a~D1u1=FqRx8@j}EYV6-Kz#o+PTh9ui$4tJLTFRG+dFgm3}aIdO>1 zHOWJyRsiD+eX((}+zo9xZiL%ZV=U}wd-b8@sr%-gtj!2u!u$dLIF2i22478!hlnx& zx7OyXgTve_OVYoW-(8_|ui&+Q2~N8KX=|C}aSD;;Dz5C5@amW{7V+ZZ^>sRe#uucu zFZ!O-ktt=eQWj2yi_WC}R1I~o$pmEHk!!a-;L?mfA3i?BUklI~VxzI4_ilAHg6V+M z>gvv8c^FlWkFdKapP0UuzVO?_frrX3e=AF0m4RLO!TUdeOL_5`^^PVJ3OYL0NI5rB zY=TEcm>fwzbx5A}XKs?lsKVjs(e0Xix+a!aHo?^@0o3g*x56P6s9I?9Rfi^{6(NoG zEhq#9_yVz(M@e6=!|!h`K#E2D|ABY~2-9NLy(D;&wFsv)H*p&Hd2>z3-#v+y9~N^7l8Xd}h_j6hBmR=)KtsbwRfEqlFp~lc?$}fLhgD zOqG z{#HBj8#oIpyshsrOOD8TW`Z$(D#m3ePg^RYwq6_4z^e8K1CBtmjMRNc_}$g@a0axV zm*RAX8pm~voD}f`PxfHC;`voHyZ{XEb$cZyiL(*Q;`WPfg+F!H^w(HAui)-%^t(?M+j=Ebo+7h%sTz+;sVK@tNVhJ;9 z&kvdYdKsOv0b&Z%8Q^nPo!gRe3gXr`zwm9Did9>m&(!nXwAE1*8RCw7#bMwt@3%?MV zEt2$)Qz7H&UKdn^G66@4P9VelFU>@RB9SpnUvpwDaQc5)BfyC{?nd&Auq!6y+;Tx7 zDp_D^zmlb0VJyP(O-gyguO(9ecRd(Ne1D523kfv>t6h9cMEtW_-Cbuw;ICvlF!zy4 zbmD(<4UtEQ5eWgwO7!10?<~-VZ2b%q(I0m;?x|~CT*pF%k1=9mrWUm*WGkp`UD@B9wSKu-~9W!b&{3t?M zio^d3Zg{9?ZA@hKb14BM(y^UP`(l%dINwbA;U`0<=xrGWY8jyfnWb`;BpoAO$Ct#E zfsE_?haD{3Y#(i#-&)pyNdxZ_=_qCzK18sePSM9RG=gQgFL_rF1v^hxv1Dm@W7u9L zCh6~}vZRoV5WhiyNzV`L9HG{v$g=VMcI965p$NVSs zZ${Jry!Yl&Y)YVX_LgrYzrN_8liM(?S>z9zFGmFGM?*5QUre<47v7&<#8h8RD}>iu z=LE`bz9yj9OsLi9EwHg?e_sDAd%{M${Qlk)MwyaLjv8_<)em|9lXL8gB7QcHrO6?E z$X!t*qQh6qEcclX61z8QAvIXFMDDK}1oZX|@y#ZedvpTJrEQMBc zk(RzJuPYg`?7*NesgliUE#?~tUF#p0tFp?F!n!2=Hk=l&Ys_ka9 zyhvezb7!RHnQKKK{;x2GOeR+hw%&(Ih+_=zo9tONzIybmk8LGCttBm$V*(0EAsc)1 zn~<4fea1~Qs{ki1Y!W4ucg>pJP3fk%Zvry_R@y8ysV}lPm~Wv60l9$F;tOezy2cJn zjl;dAiwzA-uBjmVCxD|m1EjUg@dz|rV%UgmJ3~oA2Shx?3~LZxJ`yjCg`+DUg8I2lm0(@&&GXGZ+b2r!a2l!yyqLVU;_|BA!`5P%*G&L`sDoN(`# zD0gn+&;lmFL_I<}L4U){4*o0@86?jNFwuGjiT|s-@p?bn=+R_ESAK+g{qEm4p2`BS z_=Yed*#CCnO{fVA(8GApn;rzz;9UOI>fR7OH7zQ?s{ShBuD#u_7$BT^(V! zf5$&;%?Y5RJQmttU=w#HC>tuubJ@yH5{3(pk2Q!{jXt`Ef||QglTEPW29~k$Ruk)Qq!(!Of(X+B$TtQ=g~*YkJu_ifbY z9lS4B)iXX`ZZgL;AL6pvS9~hJJxP8i=PS!j=fg=V+pWV(R5qI(aut71m`=oCt|~5` zk>FKKGpdJemAzKo7lYUzs2j1KHKOi8&gbyqW?u}aAET#7=>T5u_J3}+Jt(1epAvI9l>KRXB%TI~zraQo}hJ{2?4!tdNhXdIxPnT7KUf13$0 z2v^rTSOcU>t3*pDx6-c@%+F$fiR%9;a!CBtwuoyprzjy-SL4|rrGOB!Vma?QFMDyU6F z)nm06KNTSw;9izw>;;nXrkp!_Nbi2tsE|5Jf4;Oc&26hua1hs><)ZtI-Raj>g#J@O z&SL1QJ9BUgZc>&jl_u?H6CTMQ3eDNS5x{ABPOyNvo@YnD(gBH<6np?NQC&xzIqM0<$ z+1;Q^G*?=zQR=%2TZ!wa-F}788E}EsFl@bQE0)>BMZ0e9p2c>7C|7VS1Fq{`qDhX9 zQw>NqhgXYK@~Bo~sx^i82zC%P*OQT1TIgrFPPZ z5Ji_E=G=y{h24Q-GX1-}D>c|-i(;rS%Fb3?)A`C5`MI6CF;LR7?&0ND=clKlb#Ze6 zXl;E%s!TKYR#!-w_;Zyp-Cou#FnCczIMB^kK-5eb<=a%6skSCRj=4V>a^`Up}U8=p-&uu1^me zEfXHRe(68RrzAaXBm4j$bfnXXJ;vey+Q}4TXvx0JNv!6VGbv`R3I`;Iv<~k$6Ug&n z7|s~JUn6yR_+nDjR2L}8ey#S%xb$f0lyDGC{gM(+A#!FXvz8Hu!z?WZ);mFhz
zQiUvW=Q{CMNU?NMYqsAUXm$_39+fcJD}Lx$N)d)ZzCoG6NI5VpM}Kt@KBc1vh%Kvv zH$;9)>04zgE2>MeX>0S`EUM9Jw-xcety_A>*;x2Z!q zw;S|4KnuUAvI>0xCZ``RT{rvw1mg;XFtkTn0Os~HzV!HS7$_bFd#zcnR^ z`ho(z%B=74F;P2S*gWg58id%hi#7j~?{|U>3pY<|+Z?U!ZRSh6qF}TXPle&R zz+fEsp%YGm)A;Ns_Ez;IPveRSY9juhxqNb-K-0M_Z}xw zv7zU`wrM@Kf+Eh6CaksU7HS<93!?~r@av7ZQQ~>>jI^aRbYrfOC41Vnpu*Tb42vP; zCksGqI+?;e_H}J-d%$`J3E6bLe2xeB#FPs_2{-;TC%3xjtA+In0r+OvM^LsC)_Sar z4zb|y$5?2!AoQS!+}CXz7q)K2Q{sk2ruhj00k`Y=UchBrwvhx>&Iz0&LOn2CbBrlR zUcW!ptgnS0kVoZqXF~7pk|wcmD4%Csm28spY6syJ*WBPX%;L)4pC4eg-5%?A%1_pZ zhhUq589ETQxh@9(i?wv$#P#W~%0v0Zg$E=@{_ZZ|h~V~8`%363CYjzeq#)H^OQ_Jp z*nRW3DNkeC)B7%TN-9Ig#j%Aj3fJv?0yXdud|a5H9xl);fda{Z0AJO?zffB`KTG+g zqVDATNz#PBAqKYo#oKw;w37x_?L%#xD|kcthjtyi*?~r0_yGwecovf;5n!h?;5iP{ z?b9`Cq&0YycyNUM7@NP~QK4@UxVq}{jX98#?7F1TC^47pcejxu6e$yWAXyHtg8sCX4)=Ob7{y zQ{|qqk4T#tb>8N!$ZOYLoD8>HHn#qgcig0pPgQ{grn;P(9eJKssO~?vcLTDI%@W<; zKCO;q=zDXfgam=?V@NT@{!g+ilz`j;kktOiz=_m4r2Tgb0myCO$S0olz>z$F+x@vA z@H=0X%m%WZS*Qu_Z7qbF`T_lw&f$�!X5p5sf&LloNSTYkUfT-^- zh_&N{d?i&+lmPX!=;cz!MGhS|1g==7kGWwNh z^w2WT{v0z$%#nu2`FFRsK5%^77vxC!Gg~lv%yM zdR*gHb!2v6Q09kL;8JVQo8eaUHq;$ER;WPXYOHMAZ6@>TOKyEFoeD!PrsHLCMf4QP zwllom@mG6OO;3_4xWc5b0-9Csu_i8}89I1BRw!^l&3niiT6dz-u2bPeyIJ3>W*gWf z4f9R&yhEb8p_h>&pN`h$NN8_tyLu5VBNtDP8szPjVf_^4=Q|wRueC`>cekFU-2;1u zQ1W_tw3L73Z?oKCo#1oDy6k!*H>0a=FS)YY99nV@=!oUpk>D3hRp?#0%gv;+8SUae zGM!1)n(vZ;qhAyrTFh-wf3lVjW0T;5qypX7I@ZUz{(ZTuv`Po~e8L-tr=h?3Cn~d` zpCe$x``Ohh57zKv$u_4^;3&ToSn;w?f(DDm-)CMVfQ>FcrN}pl*8%O#18ni{y{j)l z^y{P!)3uQ!qASSRDSf%r!{K+0a&TC=;#6-0u74%DwSyg*55J9W{ga`y43x3-m z+*Xi)OP8gQZiYd8ITy1Oq|94)QpNB@az>Z%L9(>Bm*8dFWBH1MM{r}MH9Ds5nuBbO z6g>rr*72S;&+5;GG(=ZQP_2^g5~YHE=?4DXL+WBXfRimgJP!d5RI932#~(fk+}l}# zEDicd{y8NH2&dOL_U5`WwX_z+|EDrV70!ZKDn=y@Onz-<&vN?=Nd^l6?Zq!@;dFoJ z-r!)WG;p$>NQL5OA}rs!IMU<*h{#e6H~}CF2dOpSFMs&}kkKc^bAMvQJgX4OO-wih zF8wH9JpldJiFH8S6Qv5d20Kru_N*TlrUUOYH89?OSH`tw&>;4Nv*=4q5r*TIX3ygP zx{7w(dCRWn`+&SivqsE<7jSyd;|$r}Lx{r4)^1vi=jjLjLg96+@73BG;m_~Pf8d`1 zwO8+@F;Bhy&NOG!PP+^Mp;ITO@Tt-|%umsCa=A}2?yy6}_Avwpw%&lI@5@5H65n>U z&i@wlamp#EzlKMIJ?0hIztM?LU|hzMmtZ8yo2qoB<4n^v+4u1?*5sq&;kWzs{uKc= zKVS~|&YreKn5Z+ETHwLet6^fphNs6R4OC~tFd70<_tD21Jsg*tvbJR2G$`MOt`V_K zrbKO=&uHeT7aq8{Gxb;ld9|*+GTCmKcG;B)WQK01T8lf#3oa+09-A8DxKf>XRlOgw z%`#S|-Ob<#PZGJLwcGkpKvk@^7n*Zc-Z<{KmSoK{Vverh@$neE5hM3v4^5|TojD?) z1EwnR<52E^?|RLKZns*a(r~QCtSM6S@t}}f{Qo+X`v47XjP$mO|6=%cUSbJEJTrTJ zMr6=aMX&#AlZrqbkB5-V-*`ko1_ImffZj(3fP|dS)xXMSB%P2rkS~D&XE`ie{(ejL zCs``lQvhca%R8^jl>cfG>DLE6`pcxt|5w-NuOUMF@F4{GB_0*dfAg&oH|+~W{kg&@ zc~g%T`{sJ$QMTiT8XwShc)bp&Gm{ADj>+)nMlBr5nd|xG^B&bU$g3aY87_pW1lCuE z;lGQDQq3aH$&Fl&^FUFsf|84gc$9h;TYqpzQV0Zq`H$q@=&srxmSX&FUoNIZH1?8Tf``K zwKF8JOfl%89SzmMf+zBPt|wmKI;`1Hal1oENvI@Uj(&dq=qnwgWy*IcU^?UFRE^go zn`cdxx7Y7+b}?KcYRzkKH6CkC$g~e?!T>Q~OK`m(vv$E@?ivH8?u3j4Q$0=%J&YXR{0W8R;ZS@&mtC{+TaswlC z=27pM1S}iJ+oL=5=yX2LG3+cEY}M~30x3x~63qh%BC zYNxB+r8Hh&9J2eB7Ne+^9dX9$L#5g{#l|rxM%`7j))Oki39@@%zG2BLP^bKeP~YXU z=Lka9%3%CfP%I!PedaFe#Q7=rxLc&1)`>R1`Se!Yg=7cjvS+$asgFCSVYuh`r>umB z?|AhLKDR5wDBp@Yg>BpH%;;_|g;v`-?i99kg=|i7XeyF&CQ;Nv-mDX|q_{r#B5Eb= zE7uWz9#%h2&HU?DYdVEp>Gb6LsvGD8jl#9CQx1To_F3N13GHWauf(bs&Q*&P4*FHq zMn(3GxRytx^3kX)m49e}6L>C1kCzMQ>qk;eIJyjgv$<12ri1(SznblGC{%L;8OLx8 zf@7nhm}WU!;qOgwSJz3gE@ZUPrMpQzUsrQ3Jn|*r?(dTT$sh4suh0-E=I(!uyHh~B z|C1&`)P$OBL*qqMgX;)MC*K7y>{$Dg28FXmlDyQ~O0&fJbEnarb^7Eha-$Ue6E9jz zr+$SQU2@NyZJ9D&&JWr8vaB(16j6S%!`E&CaYJ%Bi}$d`BbSfx=PJX7M&;Br!Y{$U zAi_0u&2**Kefeq$}?dirnmTCtosVhh?Eo$5ouB~^OEa>9|MKmwpo<>i~B9q z4q&~9XDCxUcL#-HJz6jc4&}@?>E1V3_sQ<@LpSNL#<^D_-oC!@W1&=TnYM)4em=5RaBtHA?<9;%dsqAoRa?jP{h=EBmGX7A60bw ztls@G8E;z1QI$sRSZY4INY37|7{Jfn9Lw>UYt`1DIptw1T$=Lre~CJDR@&0-1y3q~ zNA_$M9{&x>LS+d4*8uPmxWr^6{W##xzwk~Kh_vuQ8^D6qLc#c3^=>b(=ZK2S5IFl% z$1Q{a2)qX{7aqbZ%8uND^iK+cHx&R%KBgtiK%$}>iV*RKuzQUG!{3W=fBr61gNPC5 zZ))EwKp{N85!Lfw{Tl6&s239`rxG9%uBu-9w-ph(ceiU9BK1AuR=W(qChwf-=`>LdYNJHj?MrwHy8)9Si`PkcB5B;aH$P=BC~M zUho0ZLJX^KzpuX?63%Y?{-9RjSx-a+gsUqGt7lQbrGJ!bR(}VBUILT BY: NOUS RESEARCHBUILT BYNOUS RESEARCH \ No newline at end of file diff --git a/8a4d52b2d756a11b786a67d977590d8e_MD5.svg b/8a4d52b2d756a11b786a67d977590d8e_MD5.svg new file mode 100644 index 0000000..50b64f2 --- /dev/null +++ b/8a4d52b2d756a11b786a67d977590d8e_MD5.svg @@ -0,0 +1 @@ +LANG: 中文LANG中文 \ No newline at end of file diff --git a/a1e5e56cbdcc97300e3228bc0aabc119_MD5.svg b/a1e5e56cbdcc97300e3228bc0aabc119_MD5.svg new file mode 100644 index 0000000..3e6132d --- /dev/null +++ b/a1e5e56cbdcc97300e3228bc0aabc119_MD5.svg @@ -0,0 +1 @@ +DISCORDDISCORD \ No newline at end of file diff --git a/f5fcdb3f89064840ca4ee81433cc5e03_MD5.svg b/f5fcdb3f89064840ca4ee81433cc5e03_MD5.svg new file mode 100644 index 0000000..bc46ca5 --- /dev/null +++ b/f5fcdb3f89064840ca4ee81433cc5e03_MD5.svg @@ -0,0 +1 @@ +DOCS: HERMES-AGENT.NOUSRESEARCH.COMDOCSHERMES-AGENT.NOUSRESEARCH.COM \ No newline at end of file diff --git a/raw/_processed/nousresearch-hermes-agent.md b/raw/_processed/nousresearch-hermes-agent.md new file mode 100644 index 0000000..d58516f --- /dev/null +++ b/raw/_processed/nousresearch-hermes-agent.md @@ -0,0 +1,178 @@ +[![[799a7f85a6cd2ee30f64fd9d7763519e_MD5.png]]](https://github.com/NousResearch/hermes-agent/blob/main/assets/banner.png) + +## Hermes Agent ☤ + +[![[f5fcdb3f89064840ca4ee81433cc5e03_MD5.svg]]](https://hermes-agent.nousresearch.com/docs/) [![[a1e5e56cbdcc97300e3228bc0aabc119_MD5.svg]]](https://discord.gg/NousResearch) [![[4a5c465b25cfe73154c51bd2bc8758a6_MD5.svg]]](https://github.com/NousResearch/hermes-agent/blob/main/LICENSE) [![[8411fb34fe3c1ed62e71648aed13c84b_MD5.svg]]](https://nousresearch.com/) [![[8a4d52b2d756a11b786a67d977590d8e_MD5.svg]]](https://github.com/NousResearch/hermes-agent/blob/main/README.zh-CN.md) + +**The self-improving AI agent built by [Nous Research](https://nousresearch.com/).** It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. Run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It's not tied to your laptop — talk to it from Telegram while it works on a cloud VM. + +Use any model you want — [Nous Portal](https://portal.nousresearch.com/), [OpenRouter](https://openrouter.ai/) (200+ models), [NovitaAI](https://novita.ai/) (AI-native cloud for Model API, Agent Sandbox, and GPU Cloud), [NVIDIA NIM](https://build.nvidia.com/) (Nemotron), [Xiaomi MiMo](https://platform.xiaomimimo.com/), [z.ai/GLM](https://z.ai/), [Kimi/Moonshot](https://platform.moonshot.ai/), [MiniMax](https://www.minimax.io/), [Hugging Face](https://huggingface.co/), OpenAI, or your own endpoint. Switch with `hermes model` — no code changes, no lock-in. + +| **A real terminal interface** | Full TUI with multiline editing, slash-command autocomplete, conversation history, interrupt-and-redirect, and streaming tool output. | +| --- | --- | +| **Lives where you do** | Telegram, Discord, Slack, WhatsApp, Signal, and CLI — all from a single gateway process. Voice memo transcription, cross-platform conversation continuity. | +| **A closed learning loop** | Agent-curated memory with periodic nudges. Autonomous skill creation after complex tasks. Skills self-improve during use. FTS5 session search with LLM summarization for cross-session recall. [Honcho](https://github.com/plastic-labs/honcho) dialectic user modeling. Compatible with the [agentskills.io](https://agentskills.io/) open standard. | +| **Scheduled automations** | Built-in cron scheduler with delivery to any platform. Daily reports, nightly backups, weekly audits — all in natural language, running unattended. | +| **Delegates and parallelizes** | Spawn isolated subagents for parallel workstreams. Write Python scripts that call tools via RPC, collapsing multi-step pipelines into zero-context-cost turns. | +| **Runs anywhere, not just your laptop** | Seven terminal backends — local, Docker, SSH, Singularity, Modal, Daytona, and Vercel Sandbox. Daytona and Modal offer serverless persistence — your agent's environment hibernates when idle and wakes on demand, costing nearly nothing between sessions. Run it on a $5 VPS or a GPU cluster. | +| **Research-ready** | Batch trajectory generation, trajectory compression for training the next generation of tool-calling models. | + +--- + +## Quick Install + +### Linux, macOS, WSL2, Termux + +``` +curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash +``` + +### Windows (native, PowerShell) — Early Beta + +> **Heads up:** Native Windows support is **early beta**. It installs and runs, but hasn't been road-tested as broadly as our Linux/macOS/WSL2 paths. Please [file issues](https://github.com/NousResearch/hermes-agent/issues) when you hit rough edges. For the most battle-tested Windows setup today, run the Linux/macOS one-liner above inside **WSL2**. + +Run this in PowerShell: + +``` +irm https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.ps1 | iex +``` + +The installer handles everything: uv, Python 3.11, Node.js, ripgrep, ffmpeg, **and a portable Git Bash** (MinGit, unpacked to `%LOCALAPPDATA%\hermes\git` — no admin required, completely isolated from any system Git install). Hermes uses this bundled Git Bash to run shell commands. + +If you already have Git installed, the installer detects it and uses that instead. Otherwise a ~45MB MinGit download is all you need — it won't touch or interfere with any system Git. + +> **Android / Termux:** The tested manual path is documented in the [Termux guide](https://hermes-agent.nousresearch.com/docs/getting-started/termux). On Termux, Hermes installs a curated `.[termux]` extra because the full `.[all]` extra currently pulls Android-incompatible voice dependencies. +> +> **Windows:** Native Windows is supported as an **early beta** — the PowerShell one-liner above installs everything, but expect rough edges and please file issues when you hit them. If you'd rather use WSL2 (our most battle-tested Windows path), the Linux command works there too. Native Windows install lives under `%LOCALAPPDATA%\hermes`; WSL2 installs under `~/.hermes` as on Linux. The only Hermes feature that currently needs WSL2 specifically is the browser-based dashboard chat pane (it uses a POSIX PTY — classic CLI and gateway both run natively). + +After installation: + +``` +source ~/.bashrc # reload shell (or: source ~/.zshrc) +hermes # start chatting! +``` + +--- + +## Getting Started + +``` +hermes # Interactive CLI — start a conversation +hermes model # Choose your LLM provider and model +hermes tools # Configure which tools are enabled +hermes config set # Set individual config values +hermes gateway # Start the messaging gateway (Telegram, Discord, etc.) +hermes setup # Run the full setup wizard (configures everything at once) +hermes claw migrate # Migrate from OpenClaw (if coming from OpenClaw) +hermes update # Update to the latest version +hermes doctor # Diagnose any issues +``` + +📖 **[Full documentation →](https://hermes-agent.nousresearch.com/docs/)** + +## CLI vs Messaging Quick Reference + +Hermes has two entry points: start the terminal UI with `hermes`, or run the gateway and talk to it from Telegram, Discord, Slack, WhatsApp, Signal, or Email. Once you're in a conversation, many slash commands are shared across both interfaces. + +| Action | CLI | Messaging platforms | +| --- | --- | --- | +| Start chatting | `hermes` | Run `hermes gateway setup` + `hermes gateway start`, then send the bot a message | +| Start fresh conversation | `/new` or `/reset` | `/new` or `/reset` | +| Change model | `/model [provider:model]` | `/model [provider:model]` | +| Set a personality | `/personality [name]` | `/personality [name]` | +| Retry or undo the last turn | `/retry`, `/undo` | `/retry`, `/undo` | +| Compress context / check usage | `/compress`, `/usage`, `/insights [--days N]` | `/compress`, `/usage`, `/insights [days]` | +| Browse skills | `/skills` or `/` | `/` | +| Interrupt current work | `Ctrl+C` or send a new message | `/stop` or send a new message | +| Platform-specific status | `/platforms` | `/status`, `/sethome` | + +For the full command lists, see the [CLI guide](https://hermes-agent.nousresearch.com/docs/user-guide/cli) and the [Messaging Gateway guide](https://hermes-agent.nousresearch.com/docs/user-guide/messaging). + +--- + +## Documentation + +All documentation lives at **[hermes-agent.nousresearch.com/docs](https://hermes-agent.nousresearch.com/docs/)**: + +| Section | What's Covered | +| --- | --- | +| [Quickstart](https://hermes-agent.nousresearch.com/docs/getting-started/quickstart) | Install → setup → first conversation in 2 minutes | +| [CLI Usage](https://hermes-agent.nousresearch.com/docs/user-guide/cli) | Commands, keybindings, personalities, sessions | +| [Configuration](https://hermes-agent.nousresearch.com/docs/user-guide/configuration) | Config file, providers, models, all options | +| [Messaging Gateway](https://hermes-agent.nousresearch.com/docs/user-guide/messaging) | Telegram, Discord, Slack, WhatsApp, Signal, Home Assistant | +| [Security](https://hermes-agent.nousresearch.com/docs/user-guide/security) | Command approval, DM pairing, container isolation | +| [Tools & Toolsets](https://hermes-agent.nousresearch.com/docs/user-guide/features/tools) | 40+ tools, toolset system, terminal backends | +| [Skills System](https://hermes-agent.nousresearch.com/docs/user-guide/features/skills) | Procedural memory, Skills Hub, creating skills | +| [Memory](https://hermes-agent.nousresearch.com/docs/user-guide/features/memory) | Persistent memory, user profiles, best practices | +| [MCP Integration](https://hermes-agent.nousresearch.com/docs/user-guide/features/mcp) | Connect any MCP server for extended capabilities | +| [Cron Scheduling](https://hermes-agent.nousresearch.com/docs/user-guide/features/cron) | Scheduled tasks with platform delivery | +| [Context Files](https://hermes-agent.nousresearch.com/docs/user-guide/features/context-files) | Project context that shapes every conversation | +| [Architecture](https://hermes-agent.nousresearch.com/docs/developer-guide/architecture) | Project structure, agent loop, key classes | +| [Contributing](https://hermes-agent.nousresearch.com/docs/developer-guide/contributing) | Development setup, PR process, code style | +| [CLI Reference](https://hermes-agent.nousresearch.com/docs/reference/cli-commands) | All commands and flags | +| [Environment Variables](https://hermes-agent.nousresearch.com/docs/reference/environment-variables) | Complete env var reference | + +--- + +## Migrating from OpenClaw + +If you're coming from OpenClaw, Hermes can automatically import your settings, memories, skills, and API keys. + +**During first-time setup:** The setup wizard (`hermes setup`) automatically detects `~/.openclaw` and offers to migrate before configuration begins. + +**Anytime after install:** + +``` +hermes claw migrate # Interactive migration (full preset) +hermes claw migrate --dry-run # Preview what would be migrated +hermes claw migrate --preset user-data # Migrate without secrets +hermes claw migrate --overwrite # Overwrite existing conflicts +``` + +What gets imported: + +- **SOUL.md** — persona file +- **Memories** — MEMORY.md and USER.md entries +- **Skills** — user-created skills → `~/.hermes/skills/openclaw-imports/` +- **Command allowlist** — approval patterns +- **Messaging settings** — platform configs, allowed users, working directory +- **API keys** — allowlisted secrets (Telegram, OpenRouter, OpenAI, Anthropic, ElevenLabs) +- **TTS assets** — workspace audio files +- **Workspace instructions** — AGENTS.md (with `--workspace-target`) + +See `hermes claw migrate --help` for all options, or use the `openclaw-migration` skill for an interactive agent-guided migration with dry-run previews. + +--- + +## Contributing + +We welcome contributions! See the [Contributing Guide](https://hermes-agent.nousresearch.com/docs/developer-guide/contributing) for development setup, code style, and PR process. + +Quick start for contributors — clone and go with `setup-hermes.sh`: + +``` +git clone https://github.com/NousResearch/hermes-agent.git +cd hermes-agent +./setup-hermes.sh # installs uv, creates venv, installs .[all], symlinks ~/.local/bin/hermes +./hermes # auto-detects the venv, no need to \`source\` first +``` + +Manual path (equivalent to the above): + +``` +curl -LsSf https://astral.sh/uv/install.sh | sh +uv venv .venv --python 3.11 +source .venv/bin/activate +uv pip install -e ".[all,dev]" +scripts/run_tests.sh +``` + +--- + +## Community + +- 💬 [Discord](https://discord.gg/NousResearch) +- 📚 [Skills Hub](https://agentskills.io/) +- 🐛 [Issues](https://github.com/NousResearch/hermes-agent/issues) +- 🔌 [computer-use-linux](https://github.com/avifenesh/computer-use-linux) — Linux desktop-control MCP server for Hermes and other MCP hosts, with AT-SPI accessibility trees, Wayland/X11 input, screenshots, and compositor window targeting. +- 🔌 [HermesClaw](https://github.com/AaronWong1999/hermesclaw) — Community WeChat bridge: Run Hermes Agent and OpenClaw on the same WeChat account. \ No newline at end of file diff --git a/wiki/_master-index.md b/wiki/_master-index.md index 7c3c4e4..7694c3c 100644 --- a/wiki/_master-index.md +++ b/wiki/_master-index.md @@ -21,7 +21,7 @@ This 3-hop pattern works for hundreds of articles without vector search. | [[wiki/obsidian-rag/_index\|obsidian-rag/]] | Karpathy's LLM wiki method — Obsidian RAG, setup, vs true RAG | 3 | | [[wiki/projects-overview/_index\|projects-overview/]] | All 42 Oliver Agency projects — grouped by server (optical-web-1, optical-dev, baic, box-cli) | 1 | | [[wiki/tech-patterns/_index\|tech-patterns/]] | Recurring tech stacks: FastAPI, React/Vite, Next.js, Azure AD, AI, Box, One2Edit, Redis/Celery, cost-tracker, OMG API, Payload CMS | 39 | -| [[wiki/architecture/_index\|architecture/]] | Cross-cutting architectural patterns: Docker Compose, multi-agent AI, GCP timeout, RAG, hotfolder, optical-dev deploy, cost-tracker, new-project checklist, troubleshooting playbooks, ADR log, Cloud Run Jobs | 53 | +| [[wiki/architecture/_index\|architecture/]] | Cross-cutting architectural patterns: Docker Compose, multi-agent AI, GCP timeout, RAG, hotfolder, optical-dev deploy, cost-tracker, new-project checklist, troubleshooting playbooks, ADR log, Cloud Run Jobs | 11 | | [[wiki/client-knowledge/_index\|client-knowledge/]] | Per-client notes for Ford, H&M, L'Oréal, Barclays, Ferrero, 3M, BAIC | 7 | | [[wiki/concepts/_index\|concepts/]] | Atomic knowledge extracted from Claude Code sessions | 204 | | [[wiki/connections/_index\|connections/]] | Cross-cutting insights linking 2+ concepts: FastAPI+Azure AD+Docker trinity, AI→cost-tracker, Apache+Vite basePath, GCP→REST polling, Box+hotfolder, Docker DNS+AdGuard, Celery prefork×faster_whisper memory stacking | 10 | @@ -39,6 +39,7 @@ This 3-hop pattern works for hundreds of articles without vector search. | [[wiki/shared-patterns/_index\|shared-patterns/]] | Oliver Agency standard library patterns: httpx, structlog, pydantic-settings, alembic — reuse before writing from scratch | 4 | | [[wiki/mistakes/_index\|mistakes/]] | Anti-patterns extracted from sessions — per-stack running lists (fastapi, react, docker, postgres, general, gemini) — injected at session start | 6 | +| [[wiki/ai-agents/_index\|ai-agents/]] | AI agent frameworks & products: NousResearch Hermes (self-improving loop, model-agnostic, multi-platform) | 1 | diff --git a/wiki/ai-agents/_index.md b/wiki/ai-agents/_index.md new file mode 100644 index 0000000..6a7658b --- /dev/null +++ b/wiki/ai-agents/_index.md @@ -0,0 +1,17 @@ +--- +title: "AI Agents Index" +description: "AI agent frameworks and products — beyond Anthropic: NousResearch Hermes, open-weight tool-calling models, self-improving loops" +tags: [index, ai-agents, frameworks] +created: 2026-05-18 +updated: 2026-05-18 +--- + +# AI Agents + +Third-party AI agent frameworks, products, and tools. For the Anthropic-specific Claude Agent SDK, see [[wiki/agent-sdk/overview|agent-sdk/]]. + +## Articles + +| Article | Summary | Source | Updated | +|---------|---------|--------|---------| +| [[wiki/ai-agents/hermes-agent\|hermes-agent]] | NousResearch self-improving agent — closed learning loop, model-agnostic, Telegram/Discord/CLI, serverless backends, agentskills.io | raw/nousresearch-hermes-agent.md | 2026-05-18 | diff --git a/wiki/ai-agents/hermes-agent.md b/wiki/ai-agents/hermes-agent.md new file mode 100644 index 0000000..04464e3 --- /dev/null +++ b/wiki/ai-agents/hermes-agent.md @@ -0,0 +1,157 @@ +--- +title: "Hermes Agent — NousResearch Self-Improving AI Agent" +aliases: [hermes-agent, nousresearch-hermes, openclaw-successor] +tags: [ai-agent, nousresearch, self-improving, skills, memory, telegram, multi-platform] +sources: [raw/nousresearch-hermes-agent.md] +created: 2026-05-18 +updated: 2026-05-18 +--- + +# Hermes Agent + +Open-source, self-improving AI agent by [Nous Research](https://nousresearch.com/). MIT licensed. Differentiator: **closed learning loop** — creates skills from experience, improves them during use, and builds a persistent user model across sessions. + +- GitHub: `NousResearch/hermes-agent` +- Docs: hermes-agent.nousresearch.com/docs + +--- + +## Key Takeaways + +- **Self-improving loop** — after complex tasks the agent autonomously creates/refines procedural "skills"; nudges itself to persist learnings to memory +- **Model-agnostic** — OpenRouter (200+ models), NovitaAI, NVIDIA NIM, OpenAI, Anthropic, Kimi, Hugging Face, or your own endpoint; switch with `hermes model` +- **Multi-platform** — single gateway process: Telegram, Discord, Slack, WhatsApp, Signal, Email + full TUI CLI; conversation continuity across platforms +- **Runs anywhere** — seven terminal backends: local, Docker, SSH, Singularity, Modal, Daytona, Vercel Sandbox; serverless (Modal/Daytona hibernate when idle, ~$0 between sessions) +- **Built-in cron** — natural-language scheduled tasks with delivery to any messaging platform +- **Subagents + RPC** — spawn isolated parallel subagents; Python scripts call tools via RPC (zero context cost) +- **agentskills.io** standard — skills are portable, compatible with the open Skills Hub +- **OpenClaw migration** — `hermes claw migrate` imports settings, memories, skills, API keys from `~/.openclaw` + +--- + +## Install + +```bash +# Linux / macOS / WSL2 / Termux +curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash +source ~/.bashrc +hermes +``` + +```powershell +# Windows (PowerShell, early beta) +irm https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.ps1 | iex +``` + +Installer bundles: `uv`, Python 3.11, Node.js, ripgrep, ffmpeg, MinGit (Windows only). + +--- + +## Core Commands + +| Command | Purpose | +|---------|---------| +| `hermes` | Start interactive TUI | +| `hermes model` | Choose provider + model | +| `hermes tools` | Toggle which tools are enabled | +| `hermes gateway` | Start messaging gateway (Telegram/Discord/etc.) | +| `hermes setup` | Full setup wizard | +| `hermes update` | Update to latest | +| `hermes doctor` | Diagnose issues | +| `hermes claw migrate` | Migrate from OpenClaw | + +### In-session slash commands (shared: CLI + messaging) +`/new`, `/reset`, `/model [provider:model]`, `/personality [name]`, `/retry`, `/undo`, `/compress`, `/usage`, `/insights [--days N]`, `/skills`, `/stop` + +--- + +## Learning Loop Architecture + +``` +Complex task completed + ↓ +Agent autonomously drafts skill (procedural memory) + ↓ +Skill stored in ~/.hermes/skills/ + ↓ +Used in future sessions → self-improves during use + ↓ +FTS5 full-text search across past sessions (LLM summarization) + ↓ +Honcho dialectic user modeling → deepening user profile +``` + +Skills conform to the **agentskills.io** open standard — importable/exportable across compatible agents. + +--- + +## Memory System + +- **MEMORY.md** — persistent facts the agent curates +- **USER.md** — user profile, built by [Honcho](https://github.com/plastic-labs/honcho) dialectic modeling +- **Session search** — FTS5 index over all past conversations, queried with LLM summarization +- Periodic nudges prompt the agent to persist key learnings before session ends + +--- + +## Terminal Backends + +| Backend | Use case | +|---------|---------| +| Local | Default laptop/desktop | +| Docker | Isolated container per session | +| SSH | Remote server execution | +| Singularity | HPC / GPU clusters | +| Modal | Serverless, hibernates when idle | +| Daytona | Dev environment, serverless persistence | +| Vercel Sandbox | Edge serverless | + +--- + +## OpenClaw Migration + +```bash +hermes claw migrate # interactive (full preset) +hermes claw migrate --dry-run # preview only +hermes claw migrate --preset user-data # no secrets +hermes claw migrate --overwrite # overwrite conflicts +``` + +Migrates: SOUL.md, MEMORY.md/USER.md, skills, command allowlist, messaging configs, API keys, TTS assets, AGENTS.md. + +--- + +## vs Claude Agent SDK + +| | Hermes Agent | [[wiki/agent-sdk/overview\|Claude Agent SDK]] | +|---|---|---| +| Target | End-users + developers | Developers embedding Claude in apps | +| Model | Any (OpenRouter, etc.) | Claude only | +| Interface | TUI + messaging bots | Programmatic (Python/TS `query()`) | +| Skills | Self-created, agentskills.io | Skills via settingSources / CLAUDE.md | +| Memory | Built-in (MEMORY.md + Honcho) | File-based or custom | +| Scheduling | Built-in cron | External (hooks, infra) | +| Deployment | VPS / serverless / GPU cluster | Your own infra | + +--- + +## Research Features + +- Batch trajectory generation +- Trajectory compression for fine-tuning tool-calling models +- Compatible with [[wiki/llm-models/openai-models\|OpenAI]], [[wiki/llm-models/claude-anthropic-models\|Anthropic]], and open-weight models + +--- + +## Related Tools + +- [computer-use-linux](https://github.com/avifenesh/computer-use-linux) — Linux desktop-control MCP server (AT-SPI, Wayland/X11, screenshots) +- [HermesClaw](https://github.com/AaronWong1999/hermesclaw) — WeChat bridge for Hermes + OpenClaw + +--- + +## Sources + +- `raw/nousresearch-hermes-agent.md` — official README +- Docs: hermes-agent.nousresearch.com/docs +- Skills Hub: agentskills.io