{"data":{"slug":"activeloopai-hivemind","name":"hivemind","tagline":"Hivemind turns your traces into reusable skills across agents","github_url":"https://github.com/activeloopai/hivemind","owner":"activeloopai","repo":"hivemind","owner_avatar_url":"https://avatars.githubusercontent.com/u/34816118?v=4","primary_language":"TypeScript","stars":1618,"forks":107,"topics":["ai","ai-agents","ai-memory","anthropic","artificial-intelligence","claude","claude-agent-sdk","claude-agents","claude-code-plugin","claude-skills","codex","embeddings","long-term-memory","memory-engine","openclaw","openclaw-skills","postgres","rag"],"archived":false,"github_pushed_at":"2026-09-18T01:09:40+00:00","maintenance_label":"Very active","stars_delta_30d":119,"url":"https://www.graphcanon.com/tools/activeloopai-hivemind","markdown_url":"https://www.graphcanon.com/tools/activeloopai-hivemind.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/activeloopai-hivemind","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=activeloopai-hivemind","description":"Hivemind turns your traces into reusable skills across agents","homepage_url":"https://deeplake.ai/hivemind","license":"Apache-2.0","open_issues":43,"watchers":10,"ai_summary":"A toolkit for creating and managing AI agent skills using traces and embeddings.","readme_excerpt":"## Quick start\n\nOne command, all your agents.\n\n**macOS / Linux**\n\n```bash\ncurl -fsSL https://deeplake.ai/hivemind.sh | sh\n```\n\n**Windows** — in PowerShell:\n\n```powershell\nirm https://deeplake.ai/hivemind.ps1 | iex\n```\n\n**Any platform, via npm** — for CI and Dockerfiles, or where policy blocks\npiping a downloaded script to a shell. Skips the checks the installers do, so\nNode 22+ and a writable npm prefix are on you:\n\n```bash\nnpm i -g @deeplake/hivemind && hivemind install\n```\n\nThe installer detects every supported assistant on your machine (table below), wires up the hooks, and shows a one-line consent prompt before opening a browser for sign-in. Restart your assistants after install.\n\n**Headless / CI installs:** pass an API token instead of using the browser flow:\n\n```bash\nHIVEMIND_TOKEN=<your-token> hivemind install\n\n---\n\n### Alternative install paths\n\n<details>\n  <summary><b>Claude Code plugin marketplace</b></summary>\n\nIf you prefer Claude Code's native plugin marketplace:\n\n```\n/plugin marketplace add activeloopai/hivemind\n/plugin install hivemind\n/reload-plugins\n/hivemind:login\n```\n\nAuto-updates on each session start. Manual update: `/hivemind:update`.\n</details>\n\n<details>\n  <summary><b>OpenClaw ClawHub</b></summary>\n\n```\nopenclaw plugins install clawhub:hivemind\n```\n\nThen type `/hivemind_login` in chat, click the auth link, and sign in.\n\n#### Commands\n\n| Command | Description |\n|---------|-------------|\n| `/hivemind_login` | Sign in via device flow |\n| `/hivemind_capture` | Toggle capture on/off |\n| `/hivemind_whoami` | Show current org and workspace |\n| `/hivemind_orgs` | List organizations |\n| `/hivemind_switch_org <name>` | Switch organization |\n| `/hivemind_workspaces` | List workspaces |\n| `/hivemind_switch_workspace <id>` | Switch workspace |\n| `/hivemind_update` | Check for plugin updates |\n\nAuto-recall and auto-capture are enabled by default. Data is stored in the same `sessions` table as Claude Code and Codex.\n\n#### Coexistence with `memory-core`\n\nHivemind runs **alongside** OpenClaw's built-in `memory-core` plugin. It does **not** claim the memory slot, so `memory-core`'s dreaming cron (`\"0 3 * * *\"`) and other memory-slot-dependent jobs keep working. Hivemind captures session activity and exposes its own commands; `memory-core` keeps owning recall/promotion/dreaming.\n\n#### Troubleshooting\n\n- **Hivemind seems slow or unresponsive.** Check the agent model in `~/.openclaw/openclaw.json` under `agents.defaults.model`. Hivemind makes many small tool calls per turn; a large reasoning model like Opus will feel sluggish. Recommended default: `anthropic/claude-haiku-4-5-20251001`.\n- **`openclaw model <id>` says \"plugins.allow excludes model\".** The `model` plugin CLI is disabled by default. Edit `~/.openclaw/openclaw.json` directly (key `agents.defaults.model`) and restart the gateway: `systemctl --user restart openclaw-gateway.service`.\n- **Model switch rejected as \"not allowed\".** Use the exact dated provider-prefixed ID (`anthropic/claude-haiku-4-5-20251001`, `anthropic/claude-sonnet-4-6`). Legacy IDs like `claude-3-5-haiku-latest` and unprefixed bare IDs are not on OpenClaw's allowlist.\n- **Self-update via Telegram fails with \"elevated is not available\".** `tools.elevated.allowFrom` must include `telegram` before elevated commands work from that channel. Safer alternative: run the upgrade in a local shell with `openclaw plugins update hivemind`.\n- **`npm error EACCES` during self-update.** OpenClaw was installed under a root-owned npm prefix (e.g. `/usr/lib/node_modules/openclaw`). Reinstall under a user-writable prefix, or run the update with appropriate privileges locally, not via a channel.\n</details>\n\n<details>\n  <summary><b>Codex (manual)</b></summary>\n\nTell Codex to fetch and follow the install instructions:\n\n```\nFetch and follow instructions from https://raw.githubusercontent.com/activeloopai/hivemind/main/harnesses/codex/INSTALL.md\n```\n\nOr run the installer script directly:\n\n```bash\ngit clone https://github","github_created_at":"2026-04-03T21:02:08+00:00","created_at":"2026-07-11T11:30:40.147284+00:00","updated_at":"2026-09-30T21:22:05.460255+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"}],"tags":[{"slug":"ai-agents","name":"ai-agents"},{"slug":"ai-memory","name":"ai-memory"},{"slug":"embeddings","name":"embeddings"},{"slug":"long-term-memory","name":"long-term-memory"},{"slug":"memory-engine","name":"memory-engine"}],"trust":{"provenance":{"is_fork":false,"github_id":1200802466,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T06:14:31.020Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":2,"last_release_at":"2026-09-17T23:45:24Z","stars_delta_30d":119,"open_issues_delta_30d":4},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:30:41.358Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"package.json:@modelcontextprotocol/*","observed_at":"2026-09-20T06:14:32.354Z","server_manifest":true},"scan":{"source":"repo_scan","observed_at":"2026-09-20T06:14:32.354Z"},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-09-20T06:14:32.354Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-09-20T06:14:32.354Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-20T06:14:32.354Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["- When you are working on an environment where multiple AI agents need to share and use the same set of skills derived from historical interactions or traces.","- If your project benefits from long-term memory enhancements with a focus on skills that can be transferred between different agents efficiently."],"when_not_to_use":["- When your application does not require skill reuse across multiple AI agents, as Hivemind’s forte is in enabling such cross-agent knowledge and behavior sharing.","- If you are looking for a standalone solution without integrating traces into reusable skills; Hivemind leans towards managing skills via traces."],"source":"enrich:decision_facts","observed_at":"2026-07-12T15:14:00.856Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Hivemind stands out for its capabilities in converting traces into reusable skills across multiple AI agents using embeddings."}]}}