Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
Appears on
Quick read
Latest capture 2026-10-03 03:05
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
2 paths
Agent instructions and tool configuration found in this repository.
Agent instructions 2
2 observed captures since 2026-08-15. Observed captures are shown by default.
Stars from first capture +97
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.
"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.
Claude Code Dedicated Development Harness - Achieving High-Quality Development Through an Autonomous Plan→Work→Review Cycle
Your Company Agentic Operating System
