{"items":[{"id":"cmugymsnf02hpqu0603ew1kye","slug":"hesamsheikh-octogent-octogent","name":"Octogent","description":"A thin orchestration dashboard over Claude Code for managing context, automation, and developer headspace. You need tentacles. 🦑","authorId":"gh:hesamsheikh","authorName":"hesamsheikh","version":"0.1.0","category":"Prompt","securityLevel":"Community","downloadsCount":0,"githubStars":1416,"pricePerCall":0,"manifest":{"name":"Octogent","tools":[],"category":"Prompt","entrypoint":{"type":"prompt"},"description":"A thin orchestration dashboard over Claude Code for managing context, automation, and developer headspace. You need tentacles. 🦑","permissions":[],"schemaVersion":1},"repoUrl":"https://github.com/hesamsheikh/octogent","tags":["agent-engineering","agentic-workflow","ai-agents","claude","claude-code","claude-hooks","claude-skills","codex","dashboard","prompt"],"stats":{"installVelocity7d":0,"retentionRate":0,"executions":0,"rating":null},"origin":"github","source":{"repo":"octogent","audit":{"files":["package.json","pnpm-lock.yaml"],"binaries":[],"findings":[],"packages":2,"auditedAt":"2026-09-25T12:51:49.504Z","lockfiles":["pnpm-lock.yaml"]},"forks":245,"owner":"hesamsheikh","stars":1416,"topics":["agent-engineering","agentic-workflow","ai-agents","claude","claude-code","claude-hooks","claude-skills","codex","dashboard"],"license":"MIT","fullName":"hesamsheikh/octogent","homepage":null,"language":"TypeScript","pushedAt":"2026-04-20T17:25:35Z","avatarUrl":"https://avatars.githubusercontent.com/u/41022652?v=4","crawledAt":"2026-09-25T12:51:47.082Z","openIssues":24,"manifestFile":"README.md","manifestPath":"README.md","defaultBranch":"main"},"readme":"<div align=\"center\">\n\n<img width=\"1500\" height=\"500\" alt=\"Octogent header\" src=\"./static/images/octogent-header.png\" />\n<br/>\n<br/>\n\n<strong>too many terminals, not enough tentacles</strong>\n<br />\n<br />\n\n![Last Update](https://img.shields.io/github/last-commit/hesamsheikh/octogent?label=Last%20Update&style=flat-square)\n[![TypeScript](https://img.shields.io/badge/TypeScript-5.8-3178C6?style=flat-square&logo=typescript&logoColor=white)](https://www.typescriptlang.org/)\n[![Node.js](https://img.shields.io/badge/Node.js-22+-5FA04E?style=flat-square&logo=node.js&logoColor=white)](https://nodejs.org/)\n[![Follow on X](https://img.shields.io/badge/Follow%20on-X-000000?style=flat-square&logo=x)](https://x.com/Hesamation)\n[![Discord](https://img.shields.io/badge/Discord-Open%20Source%20AI%20Builders-5865F2?style=flat-square&logo=discord&logoColor=white)](https://discord.gg/vtJykN3t)\n\n</div>\n\n# Octogent\n\nIt's really not fun to have **ten Claude Code sessions open at once**, constantly switching between them and trying to remember what each one was supposed to do. *Things get blurry fast* when one agent is doing documentation, another is touching the database, another is changing the API, and another is somewhere in the frontend. **Octogent** tries to fix that by giving each job its own <u>scoped context, notes, and task list</u>, while also making it possible for Claude Code to **spawn other Claude Code agents**, assign them work, and communicate with them.\n\n## The Vision\n\nThis repo is a personal exploration of what an AI coding environment might look like when terminal coding agents are treated as parts of a bigger orchestration layer, not the final interface by themselves. The point is not to hide **Claude Code** behind abstractions. The point is to make *multi-agent work less chaotic for the developer* on a real codebase.\n\n## Screenshots\n\n<div align=\"center\">\n<table>\n<tr>\n<td><img src=\"./static/images/preview_1.jpg\" alt=\"Screenshot 1\" width=\"100%\"/></td>\n<td><img src=\"./static/images/preview_2.jpg\" alt=\"Screenshot 2\" width=\"100%\"/></td>\n</tr>\n<tr>\n<td><img src=\"./static/images/preview_3.jpg\" alt=\"Screenshot 3\" width=\"100%\"/></td>\n<td><img src=\"./static/images/preview_4.jpg\" alt=\"Screenshot 4\" width=\"100%\"/></td>\n</tr>\n<tr>\n<td><img src=\"./static/images/preview_5.jpg\" alt=\"Screenshot 5\" width=\"100%\"/></td>\n<td><img src=\"./static/images/preview_6.jpg\" alt=\"Screenshot 6\" width=\"100%\"/></td>\n</tr>\n</table>\n</div>\n\n## What Octogent Does for You\n\n- **Creates tentacles as context layers** so agents can work with scoped markdown files instead of broad, messy chat context\n- **Uses `todo.md` as an execution surface** so tasks stay visible, trackable, and ready for delegation\n- **Runs multiple Claude Code terminals** so one developer can coordinate several coding sessions at once\n- **Spawns child agents from todo items** so parallel work has a concrete source of truth\n- **Supports inter-agent messaging** so workers and coordinators can report completion, blockers, and handoff notes\n- **Keeps agent-facing context in files** so the system is more durable than a single prompt thread\n- **Provides a local API and UI** for terminal lifecycle, persistence, websocket transport, and orchestration\n\nA **tentacle** is a folder under `.octogent/tentacles/<tentacle-id>/` that holds agent-readable markdown such as `CONTEXT.md`, `todo.md`, and any extra notes needed for that slice of the codebase.\n\nThe octopus metaphor is literal: *one octopus, many tentacles, different work happening at the same time*.\n\n## Tentacles\n\nA **tentacle** is a scoped job container. It gives one slice of work its own files, notes, and `todo.md` so the agent is not forced to reconstruct the entire codebase context from chat history.\n\nWhat it does:\n\n- keeps context local to one area such as documentation, database work, API changes, or frontend work\n- gives agents durable files they can read and update\n- provides a natural source for delegation through todo items\n\nFor the full model, s","createdAt":"2026-09-25T12:51:49.515Z","updatedAt":"2026-09-25T12:51:49.515Z"}],"total":1,"limit":24,"offset":0}