Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
OpenClaw Managed Agents — the open alternative to Claude Managed Agents & ChatGPT Workspace Agents. Any model, any cloud, open source.
| Date | Stars |
|---|---|
| 2026-07-31 | 438 |
| 2026-08-06 | 439 |
Today
+1 stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# OpenClaw Managed Agents [](https://github.com/stainlu/openclaw-managed-agents/actions/workflows/test.yaml) [](https://github.com/stainlu/openclaw-managed-agents/actions/workflows/publish-images.yaml) [](https://www.npmjs.com/package/@stainlu/openclaw-managed-agents) [](https://pypi.org/project/openclaw-managed-agents/) [](./LICENSE) The open alternative to Claude Managed Agents. Run autonomous AI agents via API — any model, any cloud, open source. Built on [OpenClaw](https://github.com/openclaw/openclaw), the most popular open-source AI agent framework. ## Demo <video src="https://github.com/user-attachments/assets/84a2e1b1-ef6a-4f20-8cbe-4dc36a6c8b77" controls></video> ## What this is **The name says it:** `openclaw-managed-agents` = **OpenClaw** (the agent runtime — multi-provider, 53 built-in skills, MCP-native, Pi's durable JSONL event log) + **Managed Agents** (the four-primitive API shape — Agent / Environment / Session / Event — that Claude Managed Agents made standard). You POST an Agent (model + system prompt + tools + MCP servers), open a Session against it, send Events, stream back Events. Under the hood: one isolated Docker container per active session running OpenClaw, SQLite for orchestrator metadata, SSE for streaming, WebSocket control plane for cancel / model-override / tool-confirmation. Session state is durable even if the live container is later evicted and respawned. Deploy anywhere Docker runs. It's the layer that turns OpenClaw from a personal AI assistant into a programmatic agent service your app can call. ## Published artifacts | Artifact | Package | |---|---| | Orchestrator image | `ghcr.io/stainlu/openclaw-managed-agents-orchestrator` | | Agent runtime image | `ghcr.io/stainlu/openclaw-managed-agents-agent` | | Limited-networking egress proxy image | `ghcr.io/stainlu/openclaw-managed-agents-egress-proxy` | | Telegram adapter image | `ghcr.io/stainlu/openclaw-managed-agents-telegram-adapter` | | TypeScript SDK | `@stainlu/openclaw-managed-agents` | | Python SDK | `openclaw-managed-agents` | | OpenAPI spec | [`openapi/openapi.yaml`](./openapi/openapi.yaml) | ## vs. Claude Managed Agents | | Claude Managed Agents | OpenClaw Managed Agents | |---|---|---| | Models | Claude only | Any — Anthropic, OpenAI, Gemini, Moonshot, DeepSeek, Mistral, xAI, Bedrock, OpenRouter, Groq, and [more](https://openclaw.ai) | | Hosting | Anthropic's cloud only | Any cloud or VPS with Docker — from $0/month (GCE free tier) to $4/month (Hetzner) | | Source | Closed | Open source (MIT) | | Platform tax | $0.08/session-hour on top of tokens | None | | Data | Anthropic's infrastructure | Your disk, your VPC, your control | | Multi-agent / subagents | Research preview (gated) | GA — children are first-class inspectable sessions | | Permission policy | `always_allow` + `always_ask` | `always_allow` + `deny` + `always_ask` | | Subagent observability | Opaque (tool result only) | First-class — every child session visible through the same API | | Agent versioning | Immutable history + archive | Immutable history + archive + optimistic concurrency on `PATCH` | | MCP servers | First-class `mcp_servers` field | First-class `mcpServers` field | | Streaming | Real SSE token deltas | Real SSE token deltas | | Restart safety | Not documented | Durable event queue, HMAC secret persistence, running-container adoption, observer-side run completion | | Per-session quotas | Not exposed | `maxCostUsdPerSession`, `maxTokensPerSession`, `maxWallDurationMs` | | Audit log | Telemetry only | Queryable `GET /v1/audit` | | OpenTelemetry | B
Excerpt of 35,351 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:a380992eb7defb03, llm:Repository description: 'OpenClaw Managed Agents — the open alternative to Claude Managed Agents & ChatGPT Workspace Agents. Any model, any cloud, open source.' Language: TypeScript. No topics provided.
matched fp:a380992eb7defb03, llm:Repository description: 'OpenClaw Managed Agents — the open alternative to Claude Managed Agents & ChatGPT Workspace Agents. Any model, any cloud, open source.' Language: TypeScript. No topics provided.
matched fp:a380992eb7defb03, llm:Repository description: 'OpenClaw Managed Agents — the open alternative to Claude Managed Agents & ChatGPT Workspace Agents. Any model, any cloud, open source.' Language: TypeScript. No topics provided.