{"data":{"slug":"framerslab-agentos","name":"agentos","tagline":"TypeScript AI agent framework providing cognitive memory and runtime tool forging with support for multi-agent orchestration","github_url":"https://github.com/framerslab/agentos","owner":"framerslab","repo":"agentos","owner_avatar_url":"https://avatars.githubusercontent.com/u/184314983?v=4","primary_language":"TypeScript","stars":670,"forks":97,"topics":["agent-framework","agent-memory","agentic-ai","ai-agent-framework","ai-agents","autonomous-agents","cognitive-memory","emergent-behavior","guardrails","hexaco","llm","llm-orchestration","long-term-memory","multi-agent","rag","runtime-tool-generation","tool-use","vector-search","voice-ai"],"archived":false,"github_pushed_at":"2026-09-18T18:26:34+00:00","maintenance_label":"Very active","stars_delta_30d":69,"url":"https://www.graphcanon.com/tools/framerslab-agentos","markdown_url":"https://www.graphcanon.com/tools/framerslab-agentos.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/framerslab-agentos","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=framerslab-agentos","description":"TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers.","homepage_url":"https://docs.agentos.sh","license":"Apache-2.0","open_issues":11,"watchers":2,"ai_summary":"AgentOS is an open-source project aiming to build intelligent autonomous agents capable of complex interaction and cognitive functions within a distributed system environment, supporting eleven LLM providers.","readme_excerpt":"## Install\n\n```bash\nnpm install @framers/agentos\n```\n\n```typescript\nimport { agent } from '@framers/agentos';\n\nconst tutor = agent({\n  provider: 'anthropic',                          // resolves to claude-sonnet-4-6 (provider default)\n  // model: 'claude-opus-4-8',                    // pin a specific model to override the default\n  instructions: 'You are a patient CS tutor.',\n  personality: { openness: 0.9, conscientiousness: 0.95 },\n  memory: { types: ['episodic', 'semantic'], working: { enabled: true } },\n});\n\n// Provider auto-detected from env when `provider` is omitted.\n\nconst session = tutor.session('student-1');\nawait session.send('Explain recursion with an analogy.');\nawait session.send('Can you expand on that?'); // remembers context\n```\n\n[Full quickstart](https://docs.agentos.sh/getting-started) * [Examples cookbook](https://docs.agentos.sh/getting-started/examples) * [API reference](https://docs.agentos.sh/api)\n\n**Sessions in 0.10.** Sessions carry a lossless conversation transcript — assistant tool calls, tool results, thinking blocks — independent of the memory subsystem, bounded by default (whole-block eviction past a ~120K-token estimate). `memory: false` no longer makes a session stateless; pass `history: false` for that. Long tool-driving loops get `session.reseed(snapshot)` (atomic history replacement with in-flight epoch guarding), `session.messages()` as checkpoint material, and per-send generation overrides (`toolChoice`, `requestTimeout`, `cache`, `cacheDiagnostics`, `blockLabel`):\n\n```ts\n// Before 0.10 — stateless unless memory was on:\nconst s = agent({ model, memory: false }).session('job-1'); // kept no history\n\n// 0.10 — sessions remember by default; opt out explicitly:\nconst stateless = agent({ model, memory: false, history: false }).session('job-1');\nconst bounded = agent({ model, history: { maxTokens: 60_000 } }).session('job-2');\nbounded.reseed([{ role: 'user', content: 'compact resume snapshot' }]);\n```\n\nCache note: history byte-stability holds for the stored transcript between eviction events; the wire request can still legitimately differ when dynamic memory context or message-mutating hooks inject per-call content.\n\n---\n\n---\n\n## License\n\n[Apache 2.0](./LICENSE)\n\n<div align=\"center\">\n\n<a href=\"https://agentos.sh\">\n  <img src=\"https://raw.githubusercontent.com/framerslab/agentos/master/assets/agentos-primary-transparent-2x.png\" alt=\"AgentOS\" height=\"40\" />\n</a>\n&nbsp;&nbsp;&nbsp;\n<a href=\"https://frame.dev\">\n  <img src=\"https://raw.githubusercontent.com/framerslab/agentos/master/assets/frame-logo-green-no-tagline.svg\" alt=\"Frame.dev\" height=\"40\" />\n</a>\n\n**Built by [Frame](https://frame.dev) * [Wilds.ai](https://wilds.ai)**\n\n</div>","github_created_at":"2025-10-28T04:35:14+00:00","created_at":"2026-07-11T11:35:04.995219+00:00","updated_at":"2026-09-20T06:23:40.760643+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":"agent-framework","name":"agent-framework"},{"slug":"cognitive-memory","name":"cognitive-memory"},{"slug":"llm-orchestration","name":"llm-orchestration"},{"slug":"multi-agent","name":"multi-agent"},{"slug":"runtime-tool-generation","name":"runtime-tool-generation"},{"slug":"tool-use","name":"tool-use"},{"slug":"vector-search","name":"vector-search"}],"trust":{"provenance":{"is_fork":false,"github_id":1084726333,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T06:23:38.287Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":1,"last_release_at":"2026-09-12T08:03:38Z","stars_delta_30d":69,"open_issues_delta_30d":2},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:35:06.213Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-20T06:23:39.313Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-20T06:23:39.313Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-09-20T06:23:39.313Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-20T06:23:39.313Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Need for cognitive memory and real-time tool generation in AI agents","Development preference for a framework using TypeScript"],"when_not_to_use":["Preferring frameworks without multi-agent orchestration support","Prioritizing environments with less than eleven LLM provider options"],"source":"enrich:decision_facts","observed_at":"2026-07-15T09:18:17.183Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"AgentOS supports eleven LLM providers with runtime tool forging capabilities for cognitive memory in TypeScript."}]}}