Top 100 Agent Runtime Repositories
Ranking
| Ranking | Project Name | Stars | Forks | Language | Open Issues | Description | Last Commit |
|---|---|---|---|---|---|---|---|
| 1 | guizang-ppt-skill | 20,820 | 1,492 | HTML | 14 | AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime. | 2026-06-02 |
| 2 | OpenSandbox | 11,931 | 995 | Python | 56 | Secure, Fast, and Extensible Sandbox runtime for AI agents. | 2026-07-09 |
| 3 | electric | 10,261 | 347 | TypeScript | 160 | The agent platform built on sync. | 2026-07-09 |
| 4 | deeplake | 9,202 | 721 | C++ | 54 | Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training. | 2026-05-21 |
| 5 | OpenShell | 7,523 | 982 | Rust | 255 | OpenShell is the safe, private runtime for autonomous AI agents. | 2026-07-10 |
| 6 | holaOS | 5,493 | 391 | TypeScript | 3 | Your super agent for work: local-first, learn your working context in mins and never forget it. | 2026-06-22 |
| 7 | rfcs | 4,298 | 8 | Python | 1 | RFCs for the Astrid agent runtime. Part of Unicity Astrid OS. | 2026-06-24 |
| 8 | archestra | 3,960 | 1,107 | TypeScript | 35 | Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator | 2026-07-10 |
| 9 | cascadeflow | 3,240 | 675 | Python | 2 | Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop. | 2026-07-01 |
| 10 | agentcore-samples | 3,172 | 1,231 | Python | 190 | Amazon Bedrock Agentcore accelerates AI agents into production with the scale, reliability, and security, critical to real-world deployment. | 2026-07-09 |
| 11 | docker-agent | 3,153 | 405 | Go | 4 | AI Agent Builder and Runtime by Docker Engineering | 2026-07-09 |
| 12 | agent-sandbox | 3,115 | 394 | Go | 105 | agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes. | 2026-07-10 |
| 13 | china-dictatorship | 3,091 | 293 | HTML | 825 | 反中共政治宣传库。Anti Chinese government propaganda. 住在中国真名用户的网友请别给星星，不然你要被警察请喝茶。常见问答集，新闻集和饭店和音乐建议。卐习万岁卐。冠状病毒审查郝海东新疆改造中心六四事件法轮功 996.ICU709大抓捕巴拿马文件邓家贵低端人口西藏骚乱。Friends who live in China and have real name on ac... | 2026-02-05 |
| 14 | openocta | 2,976 | 329 | TypeScript | 22 | Open-source work buddy. Open-source personal desktop AI agent.Double-click install, instant boot, data stays local. Go runtime for office/ITops/marketing workflows. | 2026-07-10 |
| 15 | HotswapAgent | 2,602 | 523 | Java | 106 | Java unlimited redefinition of classes at runtime. | 2026-02-15 |
| 16 | harmonist | 2,183 | 229 | Python | 0 | Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies. | 2026-06-09 |
| 17 | css | 1,940 | 44 | TypeScript | 0 | The markup-driven CSS language and framework — readable by humans, reliable for agents. | 2026-07-09 |
| 18 | .github | 1,937 | 151 | - | 0 | 这里是GitHub的草场，也是戈戈圈爱好者的交流地，主要讨论动漫、游戏、科技、人文、生活等所有话题，欢迎各位小伙伴们在此讨论趣事。This is GitHub grassland, and the community place for Gege circle lovers, mainly discusses anime, games, technology, lifing and other t... | 2025-10-04 |
| 19 | ClawManager | 1,917 | 148 | Go | 14 | A Kubernetes-native control plane for AI agent instance management, with governed AI access, runtime orchestration, and reusable resources across multiple agent runtimes. | 2026-07-08 |
| 20 | ax | 1,846 | 105 | Go | 31 | Google's open source distributed agent runtime | 2026-07-10 |
| 21 | bub | 1,536 | 145 | Python | 3 | Bub it. Build it. A hook-first runtime for agents that live alongside people. | 2026-07-07 |
| 22 | poco-claw | 1,346 | 126 | Python | 0 | A more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, a sandboxed runtime and channel-based team collaboration. Under the hood, it is powered by ... | 2026-06-18 |
| 23 | overstory | 1,331 | 211 | TypeScript | 16 | Multi-agent orchestration for AI coding agents — pluggable runtime adapters for Claude Code, Pi, and more | 2026-05-28 |
| 24 | sre | 1,284 | 197 | TypeScript | 6 | The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across... | 2026-04-03 |
| 25 | shepherd | 1,247 | 80 | Python | 4 | A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write f... | 2026-07-09 |
| 26 | commonly | 1,182 | 163 | TypeScript | 29 | Open-source workspace where your agents and team share one memory. Any runtime, your infra — self-host in one command, no per-agent fees. | 2026-07-09 |
| 27 | PhoneClaw | 1,137 | 155 | Swift | 1 | PhoneClaw turns phones into local AI agent runtimes with on-device models, native mobile Skills, LiveLand, and optional Mac Gateway inference. | 2026-07-08 |
| 28 | archive | 1,105 | 99 | Python | 4 | Skill Compose is an open-source agent builder and runtime platform for skill-powered agents. No workflow graphs. No CLI. | 2026-03-04 |
| 29 | Ai-Agent-Skills | 1,091 | 125 | JavaScript | 0 | Universal skill installer and package manager for AI coding agents. One command, 12+ runtimes. npx ai-agent-skills | 2026-05-05 |
| 30 | OpenRath | 1,080 | 47 | Python | 0 | An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows. | 2026-07-08 |
| 31 | Hexabot | 1,049 | 220 | TypeScript | 14 | Hexabot v3 is an AI workflow automation platform, combining workflows, actions, agents, and conversational channels in one runtime. | 2026-07-09 |
| 32 | compose-for-agents | 990 | 449 | TypeScript | 8 | Build and run AI agents using Docker Compose. A collection of ready-to-use examples for orchestrating open-source LLMs, tools, and agent runtimes. | 2026-06-04 |
| 33 | tensorlake | 959 | 138 | Python | 42 | Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications | 2026-07-09 |
| 34 | boop-agent | 869 | 202 | TypeScript | 4 | iMessage personal agent: choose Claude Agent SDK (Claude Code) or Codex app-server runtime (Codex/ChatGPT), with memory, sub-agents, automations, integrations. | 2026-07-01 |
| 35 | xpander.ai | 867 | 126 | Jupyter Notebook | 1 | xpander.ai is the runtime and control plane to build, run, and ship reliable AI agents fast and anywhere | 2025-11-11 |
| 36 | kweaver-core | 837 | 112 | Go | 80 | KWeaver Core is a harness-first foundation for enterprise decision agents. It turns fragmented data, knowledge, tools, and policies into governed context, safe execution, and verifiable feedback loops... | 2026-05-29 |
| 37 | golf | 833 | 69 | Python | 0 | Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents | 2026-05-08 |
| 38 | agentscope-runtime | 831 | 163 | Python | 55 | A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility. | 2026-06-04 |
| 39 | evotown | 830 | 77 | Python | 35 | a middle platform for enterprise Agent runtime governance and capability assets — connect OpenClaw, Hermes, SkillLite, and custom runtimes in one place; accumulate Skills and enterprise knowledge; pro... | 2026-07-10 |
| 40 | ClawProBench | 811 | 52 | Python | 0 | ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability. | 2026-06-28 |
| 41 | hermes-browser-extension | 777 | 63 | JavaScript | 0 | Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime. | 2026-07-09 |
| 42 | bedrock-agentcore-sdk-python | 739 | 129 | Python | 66 | Python SDK for transforming any AI agent into a production-ready application. Framework-agnostic primitives for runtime, memory, authentication, and tools with AWS-managed infrastructure. | 2026-07-09 |
| 43 | DongTai-agent-java | 699 | 205 | Java | 11 | Java Agent is a Java application probe of DongTai IAST, which collects method invocation data during runtime of Java application by dynamic hooks. | 2023-12-25 |
| 44 | wanman | 653 | 105 | TypeScript | 9 | wanman is an open-source agent matrix runtime inspired by Japanese one-man trains. It lets human users step back into an observer role while local agent runtimes coordinate autonomous multi-agent work... | 2026-06-14 |
| 45 | ai00_server | 619 | 73 | Rust | 16 | The all-in-one RWKV runtime box with embed, RAG, AI agents, and more. | 2026-06-09 |
| 46 | mda | 610 | 32 | TypeScript | 1 | MDA Open Spec — a Markdown superset for agent-facing documents. One .mda source compiles to drop-in SKILL.md, AGENTS.md, MCP-SERVER.md, and CLAUDE.md. JSON Schema validated, with typed dependency grap... | 2026-05-26 |
| 47 | swarmclaw | 609 | 129 | TypeScript | 5 | Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, ... | 2026-06-30 |
| 48 | agentos | 591 | 88 | TypeScript | 1 | TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers. | 2026-07-10 |
| 49 | agentcookie | 590 | 51 | Go | 0 | Your agent runs on a Mac that isn't your daily driver. agentcookie keeps its sessions in sync with the Mac you actually browse on, continuously, encrypted over Tailscale, so OpenClaw, Hermes, or any o... | 2026-06-26 |
| 50 | pi-gui | 587 | 86 | TypeScript | 9 | Electron GUI app for the pi coding agent runtime | 2026-07-05 |
| 51 | ironcurtain | 552 | 74 | TypeScript | 3 | A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev) | 2026-07-08 |
| 52 | fullstack-solution-template-for-agentcore | 549 | 167 | Python | 9 | Flexible Fullstack solution template for production-ready deployments of any use case on Amazon Bedrock AgentCore. | 2026-07-09 |
| 53 | harness-engineering-guide | 530 | 65 | TypeScript | 1 | 🔧 The open guide to Harness Engineering — concepts, tutorials, papers, tools, and resources for building and managing AI agent runtimes. | 2026-04-19 |
| 54 | claw-orchestrator | 526 | 81 | TypeScript | 0 | Run Claude Code, Codex, Gemini, Cursor Agent and custom coding CLIs as one unified runtime for claw-style agent systems. Runs standalone, with first-class OpenClaw plugin support. | 2026-07-10 |
| 55 | clawless | 515 | 91 | TypeScript | 4 | ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers | 2026-07-08 |
| 56 | LockKnife | 507 | 108 | Python | 1 | LockKnife: The Ultimate Android Security Research Tool. A unified TUI workspace and headless CLI for deep Android security research, built for researchers and hackers. Powered by Python orchestration ... | 2026-06-14 |
| 57 | agentspan | 493 | 44 | TypeScript | 15 | Durable, Distributed runtime for ALL of your agents - OpenAI, ADK, Langchain, Vercel, etc. | 2026-07-10 |
| 58 | aislop | 476 | 19 | TypeScript | 2 | Catch the slop AI coding agents leave in your code: narrative comments, swallowed exceptions, as-any casts, dead code, oversized functions. 50+ rules across 8 languages (TypeScript, JavaScript, Python... | 2026-07-04 |
| 59 | opencowork | 474 | 2 | TypeScript | 0 | Open-source, local-first desktop Agent Runtime for turning business goals into executable, reusable, and auditable workflows. | 2026-06-05 |
| 60 | sandboxed.sh | 465 | 49 | Rust | 15 | Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets, and OKX read-only security checks. | 2026-07-09 |
| 61 | bug-hunter | 454 | 52 | JavaScript | 0 | Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities... | 2026-05-01 |
| 62 | xcrawl-skills | 446 | 43 | - | 0 | Reusable Xcrawl skill definitions for multi-agent runtimes, focused on API-first web data workflows. | 2026-03-20 |
| 63 | openclaw.net | 436 | 82 | C# | 0 | Self-hosted Personal AI + agent runtime in .NET (NativeAOT-friendly) | 2026-07-10 |
| 64 | agentguard | 435 | 65 | TypeScript | 5 | Security guard for AI agents — blocks malicious skills, prevents data leaks, protects secrets. 24 detection rules, runtime action evaluation, trust registry. | 2026-06-25 |
| 65 | station | 426 | 41 | Go | 7 | Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control. | 2026-01-27 |
| 66 | ai4j | 422 | 55 | Java | 0 | 一款JavaSDK用于快速接入AI大模型应用，整合多平台大模型，如OpenAi、智谱Zhipu(ChatGLM)、深度求索DeepSeek、月之暗面Moonshot(Kimi)、腾讯混元Hunyuan、零一万物(01)等等，提供统一的输入输出(对齐OpenAi)消除差异化，优化函数调用(Tool Call)，优化RAG调用、支持向量数据库(Pinecone)、内置联网增强，并且支持JDK1.8，为... | 2026-07-06 |
| 67 | Amis | 421 | 7 | TypeScript | 0 | 🖥️ A local-first desktop workspace for private agents, local models, runtime visibility, and local/cloud routing. | 2026-06-24 |
| 68 | live-swe-agent | 411 | 41 | - | 7 | Live-SWE-agent: live, runtime self-evolving software engineering agent | 2026-01-19 |
| 69 | mobileClaw | 403 | 17 | Kotlin | 4 | Open Android AI agent runtime for phone control, app automation, VLM screen reading, skill routing, mini apps, and Mihomo VPN workflows. | 2026-07-09 |
| 70 | trinity | 389 | 61 | Python | 145 | Self-hosted runtime for autonomous Claude Code (and other CLI) AI agents. Apache 2.0. | 2026-07-09 |
| 71 | clawmetry | 387 | 63 | Python | 64 | See your agent think. Real-time observability for 12 AI agent runtimes - OpenClaw, NVIDIA NemoClaw, Claude Code, Codex & 8 more. | 2026-07-10 |
| 72 | Adrian | 383 | 78 | Python | 3 | Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts. | 2026-07-01 |
| 73 | activegraph | 380 | 31 | Python | 1 | Event-sourced graph runtime for durable and stateful agents | 2026-07-10 |
| 74 | kode-agent-sdk | 379 | 69 | TypeScript | 5 | Open runtime for building Claude Code & Manus like Agent Product | 2026-05-11 |
| 75 | pabar_agent_runtime | 372 | 0 | - | 0 | agent runtime | 2026-06-16 |
| 76 | homerail | 365 | 78 | TypeScript | 2 | Voice-first local agent orchestration runtime for auditable DAG workflows. | 2026-07-10 |
| 77 | Aegis | 363 | 37 | TypeScript | 1 | Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes. ... | 2026-07-09 |
| 78 | china-dictatroship-7 | 354 | 38 | HTML | 45 | 反中共政治宣传库。Anti Chinese government propaganda. https://github.com/cirosantilli/china-dictatorship 的备份backup. 住在中国真名用户的网友请别给星星，不然你要被警察请喝茶。常见问答集，新闻集和饭店和音乐建议。卐习万岁卐。冠状病毒审查郝海东新疆改造中心六四事件法轮功 996.ICU709大抓捕巴拿马文件... | 2026-02-05 |
| 79 | marionette_mcp | 345 | 37 | Dart | 4 | MCP server enabling AI agents to interact with Flutter apps at runtime - let them inspect widgets, simulate taps, enter text, scroll, and take screenshots. | 2026-07-03 |
| 80 | .config | 345 | 99 | Shell | 39 | # # Automatically generated file; DO NOT EDIT. # OpenWrt Configuration # CONFIG_MODULES=y CONFIG_HAVE_DOT_CONFIG=y # CONFIG_TARGET_sunxi is not set # CONFIG_TARGET_apm821xx is not set # CONFIG_TARGET_... | 2023-10-05 |
| 81 | agent-systems-handbook | 326 | 58 | MDX | 9 | A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend ... | 2026-07-05 |
| 82 | agentscope-samples | 324 | 89 | Python | 10 | A collection of ready-to-use Python sample agents built with AgentScope and AgentScope Runtime, covering use cases from CLI tools to full-stack applications. | 2026-04-10 |
| 83 | devo | 307 | 131 | Rust | 17 | Open-source, model-neutral agent desktop/runtime for private, enterprise, and OpenAI-compatible model environments. Supports DeepSeek, Qwen, Kimi, Anthropic-compatible APIs, MCP, and local code search... | 2026-07-08 |
| 84 | clawshell | 299 | 23 | Rust | 0 | The Runtime Security Layer for OpenClaw/Hermes-agent, the essential safety harness for PII & sensitive credentials protection. | 2026-07-09 |
| 85 | capsule | 292 | 20 | Rust | 0 | Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments. | 2026-06-19 |
| 86 | ai-functions | 290 | 29 | Python | 0 | Python functions powered by AI agents - with runtime post-conditions for reliable agentic workflows. | 2026-07-06 |
| 87 | cashclaw | 290 | 106 | JavaScript | 0 | The Agent Economy Layer — agents earn, agents spend, Guard protects. 13 skills, runtime cost cap, recursive kill, tool firewall. 50+ HYRVE API endpoints, job polling daemon, MPP stablecoin. v1.7.0 | 2026-05-19 |
| 88 | prax-agent | 289 | 34 | Python | 0 | Self-improving agent runtime that learns from experience — test-verify-fix loops, correction detection, cross-project memory, multi-model orchestration. | 2026-06-01 |
| 89 | xinfer | 285 | 40 | Rust | 52 | Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime. | 2026-07-10 |
| 90 | DashClaw | 284 | 50 | TypeScript | 2 | 🛡️The governance runtime for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit-ready decision trails. | 2026-07-10 |
| 91 | Linghun | 277 | 26 | TypeScript | 0 | AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification. | 2026-07-08 |
| 92 | atomic | 277 | 43 | TypeScript | 19 | The verifiable coding agent runtime. Build your own software factory with verification built in. Run verifiable engineering loops with control and confidence. Define the work as stages, checks, gates,... | 2026-07-10 |
| 93 | agent-control | 274 | 42 | Python | 18 | Centralized agent control plane for governing runtime agent behavior at scale. Configurable, extensible, and production-ready. | 2026-07-08 |
| 94 | agbcloud-sdk | 274 | 23 | Python | 0 | AI-native cross-platform sandboxes for developers, featuring multimodal cloud runtime and expert agents. | 2026-04-07 |
| 95 | agent-runtime | 271 | 50 | Python | 0 | Standalone agent runtime core with neutral LLM types, provider clients, tool loop, and extension protocols. | 2026-07-01 |
| 96 | argus | 264 | 26 | Python | 0 | A recursive evidence-gated cognitive runtime for memory-native AI agents, combining hybrid retrieval, temporal reasoning, async learning, and plug-and-play tools. | 2026-06-09 |
| 97 | ai-app-bridge | 258 | 5 | JavaScript | 0 | AI App Bridge is a runtime bridge for AI agents to close the loop on mobile app iteration: inspect the running app, operate UI and WebView surfaces, collect structured runtime state, verify results, a... | 2026-07-07 |
| 98 | Containarium | 253 | 17 | Go | 15 | Open-source agent runtime — SSH-native isolation, eBPF egress policy, Kubernetes + LXC backends, GPU passthrough, MCP-native CLI | 2026-07-10 |
| 99 | statewave | 247 | 11 | Python | 1 | Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs. | 2026-07-09 |
| 100 | omnicoreagent | 244 | 57 | Python | 1 | Open Python agent harness for production AI apps: tools, MCP, memory, workspace, telemetry, subagents, background tasks, and OmniServe APIs. | 2026-05-29 |