Agent harnessSoftware development
openharness
Run a reversible terminal coding agent with local or cloud LLMs.
- Stars
- 95
- Forks
- 21
- Updated
- Updated Jul 9, 2026
MIT
Run a reversible terminal coding agent with local or cloud LLMs.
OpenHarness connects to local models such as Ollama or to cloud APIs, then reads, edits, and searches code, runs commands, uses MCP servers, delegates to sub-agents, and operates headlessly in CI. Permission modes, command-risk analysis, file checkpoints, automatic Git commits, and post-edit verification make agent changes easier to inspect and undo. It requires Node.js 18+.
Resource types
Use cases
Runtime
Build and inspect an agent-maintained Rust experiment around the `claw` CLI.
Run, switch, and automate coding agents across local and remote backends.
Protocols & integrations
Capabilities
Public GitHub facts last synced Jul 10, 2026.
Orchestrates agents, memory, tools, and automated workflows around Claude Code and Codex.
A coding-agent kanban and isolated-workspace tool that has announced it is sunsetting.