{"data":{"slug":"shyftlabs-continuum","name":"continuum","tagline":"Agent runtime by ShyftLabs","github_url":"https://github.com/shyftlabs/continuum","owner":"shyftlabs","repo":"continuum","owner_avatar_url":"https://avatars.githubusercontent.com/u/64531234?v=4","primary_language":"Python","stars":84,"forks":11,"topics":["agent-framework","agentic-ai","ai-agents","ai-orchestration","anthropic","enterprise-ai","human-in-the-loop","kimi-k2","llama","llm","llm-framework","llm-observability","llmops","mcp","multi-agent","openai","qwen","temporal"],"archived":false,"github_pushed_at":"2026-09-10T19:21:05+00:00","maintenance_label":"Very active","stars_delta_30d":5,"url":"https://www.graphcanon.com/tools/shyftlabs-continuum","markdown_url":"https://www.graphcanon.com/tools/shyftlabs-continuum.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/shyftlabs-continuum","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=shyftlabs-continuum","description":"Continuum — the agent runtime by ShyftLabs. Build, orchestrate, ship.","homepage_url":"https://docs.continuum.shyftlabs.io/","license":"Apache-2.0","open_issues":14,"watchers":0,"ai_summary":"Continuum is an agent runtime for building and orchestrating AI agents.","readme_excerpt":"## 🚀 Quick start\n\n**Requirements:** Python 3.13+ and Docker (for Redis · Qdrant/Milvus · Langfuse).\n\n```bash\npython3.13 -m venv .venv && source .venv/bin/activate\npip install shyftlabs-continuum\n\ncontinuum up                 # start local infra (Redis + Qdrant); writes ./.env\necho \"OPENAI_API_KEY=sk-…\" >> .env   # add your provider key(s) — see Configuration below\n```\n\n`continuum up` ships with the package — it locates the bundled Docker stack and starts\nit for you, so there's no compose file to find or copy. It defaults to the **minimal**\nprofile (Redis + Qdrant); pick a bigger one with `continuum up standard` / `continuum up full`.\n\n> **Contributors** working from a clone: `git clone https://github.com/shyftlabs/continuum.git && cd continuum`,\n> then `python3.13 -m venv .venv && source .venv/bin/activate`, `pip install -e \".[dev]\"`,\n> `cp .env.template .env`, and `continuum up`.\n\n#### Infrastructure profiles\n\n| Command | Services started | Use it when |\n|---|---|---|\n| `continuum up` *(minimal)* | Redis + Qdrant (2 containers) | Day-to-day development — a stateful agent with memory, nothing heavy. |\n| `continuum up standard` | minimal + Langfuse stack (8) | You want tracing/observability in the [Langfuse UI](http://localhost:3000). |\n| `continuum up full` | everything (13), incl. Temporal + Milvus | Durable workflows (Temporal) or the Milvus vector store. |\n\nEach profile also writes a managed block to `./.env` (`VECTOR_STORE_PROVIDER`, `LANGFUSE_ENABLED`, …)\nso the SDK only talks to services that are actually running. Other commands:\n`continuum down [-v]`, `continuum status`, `continuum logs [service] [-f]`, `continuum config-path`.\n\n**Port conflicts?** Every published host port is overridable via `.env` (defaults shown):\n`SESSION_REDIS_PORT=6380`, `QDRANT_PORT=6333`, `QDRANT_GRPC_PORT=6334`, `MILVUS_PORT=19530`,\n`LANGFUSE_WEB_PORT=3000`, `LANGFUSE_WORKER_PORT=3030`, `LANGFUSE_POSTGRES_PORT=5433`,\n`LANGFUSE_REDIS_PORT=6382`, `CLICKHOUSE_HTTP_PORT=8123`, `CLICKHOUSE_NATIVE_PORT=9000`,\n`MINIO_API_PORT=9090`, `MINIO_CONSOLE_PORT=9091`, `TEMPORAL_PORT=7233`, `TEMPORAL_UI_PORT=8233`,\n`TEMPORAL_POSTGRES_PORT=5434`. For the stores the SDK connects to (`QDRANT_PORT`, `MILVUS_PORT`,\n`SESSION_REDIS_PORT`), the same variable drives both the container and the client, so they stay in sync.\n\nYour first agent:\n\n```python\nimport asyncio\nfrom continuum.agent import BaseAgent, AgentRunner\n\nasync def main():\n    agent = BaseAgent(\n        name=\"hello-agent\",\n        instructions=\"You are a friendly assistant.\",\n        model=\"gpt-4o-mini\",\n    )\n    runner = AgentRunner()\n    response = await runner.run(agent, \"Hi!\")\n    print(response.content)\n\nasyncio.run(main())\n```\n\n`AgentRunner.run()` returns an `AgentResponse` with `content`, `structured_output`, `usage`, `tool_calls`, `run_artifacts`, `latency_ms`, and the full handoff chain. See the [**docs**](https://docs.continuum.shyftlabs.io/) for streaming, tools/MCP, memory, handoffs, and workflows.\n\n---\n\n## 📄 License\n\nLicensed under the [Apache License, Version 2.0](https://github.com/shyftlabs/continuum/blob/main/LICENSE). Copyright © 2025–2026 [ShyftLabs Inc.](https://shyftlabs.io/)\n\nFor commercial / enterprise inquiries — SLAs, indemnification, hosted offerings, custom features — contact **[continuum@shyftlabs.io](mailto:continuum@shyftlabs.io)**.\n\n<div align=\"center\">\n<br />\n<sub>Built with ❤️ by <a href=\"https://shyftlabs.io/\">ShyftLabs</a> · <a href=\"mailto:continuum@shyftlabs.io\">continuum@shyftlabs.io</a></sub>\n</div>","github_created_at":"2026-05-26T19:16:56+00:00","created_at":"2026-07-15T10:41:36.982407+00:00","updated_at":"2026-09-20T04:25:32.73074+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"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"agent-framework","name":"agent-framework"},{"slug":"agentic-ai","name":"agentic-ai"},{"slug":"ai-agents","name":"ai-agents"},{"slug":"llm-framework","name":"llm-framework"}],"trust":{"provenance":{"is_fork":false,"github_id":1250579815,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-11T06:00:06.004Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":3,"days_since_push":0,"last_release_at":"2026-07-20T18:51:01Z","stars_delta_30d":5,"open_issues_delta_30d":2},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":68,"high_count":0,"last_scan_at":"2026-07-15T10:41:38.630Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-11T06:00:06.529Z"},"deploy":{"source":"dockerfile:docker-compose.yml","self_host":true,"observed_at":"2026-09-11T06:00:06.529Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-11T06:00:06.529Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-11T06:00:06.529Z"},"has_docker":{"value":true,"source":"dockerfile:docker-compose.yml","observed_at":"2026-09-11T06:00:06.529Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-11T06:00:06.529Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Python version 3.13+ required."],"min_ram_gb":null,"requires_docker":true},"constraints":{"min_ram_gb":null,"requires_docker":true},"when_to_use":["Use Continuum when you require fine-grained control over the operational environments of your AI agents through its minimal, standard, or full infrastructure profiles.","If your project benefits from built-in observability layers like Langfuse for tracing and logging during agent operations, Continuum's integration provides this out-of-the-box."],"when_not_to_use":["Avoid using Continuum if you prefer a setup without Docker dependencies for running your AI agents as it heavily relies on Dockerized infrastructure.","If the specific use case does not need extensive observability or complex runtime configurations, then alternatives with less overhead might be more suitable."],"source":"enrich:decision_facts","observed_at":"2026-07-16T21:10:48.868Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":true},"decision_summary":[{"label":"Requirements","value":"Requires Docker; Python version 3.13+ required."},{"label":"Adopt for","value":"Continuum is an agent runtime platform by ShyftLabs for building and orchestrating AI agents using Dockerized infrastructure profiles to manage dependencies and environment configurations."},{"label":"License detail","value":"Continuum is available under the Apache License 2.0, allowing for broad usage with attribution required."}]}}