* [OpenCodeReview v1.10.0](https://github.com/alibaba/open-code-review) – AI-powered CLI that reviews Git diffs using LLM agents and deterministic pipelines to produce precise, line-level structured comments.

* [qm v0.1.5](https://github.com/yc-software/qm) – Multiplayer agent harness that provides isolated per-user workspaces with scoped memory, files, permissions, and background tasks across Slack and the web.

* [Munder Difflin v0.4.0](https://github.com/chaitanyagiri/munder-difflin) – Local desktop harness that runs Claude Code terminals as collaborating autonomous agents with shared memory and a GOD orchestrator.

* [Agenvoy v0.32.0](https://github.com/agenvoy/Agenvoy) – Go-based AI agent framework with self-improving error memory, multi-provider LLM routing, script/HTTP tool extensions, and OS-native sandboxing.

* [GoRaven v0.4.0](https://github.com/8treenet/goraven) – Self-hosted team agent platform that provides isolated workspaces and a unified runtime for multi-agent workflows with tools, knowledge retrieval, and real task execution.

* [TrueForge charts/trueforge@0.1...](https://github.com/truefoundry/trueforge) – TrueForge is an agent harness that runs the execution loop with model calls, MCP tools, skills, sandboxing, approvals, and session state via chat UI and APIs.

* [Eve eve@0.33.0](https://github.com/vercel/eve) – Filesystem-first framework for building durable AI agents, placing core capabilities in conventional directories for easy inspection, extension, and operation.

* [NeuroBook v0.9.6-canary.202608...](https://github.com/notnotype/neuro-book) – AI-powered workspace that combines long-form writing workflows with linting and an agent-driven process for producing and managing content.