agent-runtime
21 servers · 1,927★ total
Open-source CMA-compatible agent runtime for any model, with MCP tools, sandboxed sessions, audit, replay, and a local console. Includes a native DeepSeek Harness bundle over stdio MCP.
Harness-oriented agent system framework for production-grade LLM agent applications
🛡️ The approval and policy layer for AI agents. Intercept risky actions before they run, block them, or approve them remotely.
Open-source agent runtime — SSH-native isolation, eBPF egress policy, Kubernetes + LXC backends, GPU passthrough, MCP-native CLI
Evidence-gated runner for Codex, Claude Code, OpenCode, and local coding agents. Routes tasks into scoped DAG lanes with replayable artifacts.
Make AI coding agents safe to scale autonomously: assign work, cap spend, enforce policy, verify output, roll back failures, learn from loops, and prove ROI across every repo.
Agent-first, English-canonical handbook for DeepSeek Harness with multilingual foundations, source-backed guides, and production runbooks.
Self-hosted platform for MCP Apps and agent automations — tools, interactive UIs, scheduled runs, multi-agent delegation.
The agent that learns how you decide - and proves it by never deciding for you. A local-first, loop-native runtime for a team of AI agents on your machine.
An agent runtime designed for tool-driven loop engineering.
Agentic AI orchestration framework for offensive security and CTF work, with Codex-ready skills, typed MCP servers, workflow CLIs, and OpenCROW Constellation for multi-agent coordination, corpus sync, and final artifact handoff.
Open-source context engineering protocol for AI agents: governed retrieval, bounded multi-agent handoffs, MCP, provenance, recoverable effects, and replay.
The open-source autonomy kernel MELRA — Modular Execution Layer for Reliable Autonomy. An agent-independent effect runtime for governed, durable, and verifiable autonomous execution. MELRA begins where the tool call leaves the model loop.
Self-contained multi-agent AI orchestration runtime for .NET. CLI + web UI, native tools, sandboxing, MCP, layered memory.
LiAgent OS is a local-first AI agent OS for building a private personal assistant with governed autonomy across local models and hybrid cloud services. It brings conversation, tool use, multi-agent orchestration, task scheduling, heartbeat execution, human approval, and auditability into one long-lived loop.
Agents change faster than audits. Ancilis discovers what agents can do, classifies the data they touch, activates the right controls, and continuously proves compliance. Trust your agents in production.
Headless multi-provider LLM agent runtime. Single Go binary, 16+ providers, 59+ extension hooks, zero opinions.
Open-source Go agent runtime for autonomous AI systems and multi-agent automation. MCP, RAG, 15+ LLM providers and 60+ built-in tools in a single binary.
The design intelligence runtime for AI agents. 49 rules. Zero LLM. MCP-native. Give your agent eyes.
Open-source control plane for self-hosted AI Agents: registry, runs, workflows, User Tokens, A2A/MCP APIs, and reliable Runtime Worker routing.