* [Grasp v2.0.0](https://github.com/cocofhu/grasp) – Project-management and multi-agent workflow platform with a visual requirement-clarification canvas, human approval gates, and pluggable agent backends to speed understanding and delivery.

* [Agenvoy v1.2.0](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.

* [OpenCodeReview v1.12.13](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.

* [OpenCodeReview v1.12.12](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.

* [Eve eve@0.76.0](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.

* [Harness Mix v0.4.1](https://github.com/emo-xiaoyu/harness-mix) – Codex Desktop-style coding harness that provides a host runtime and protocol core across Windows, macOS, and Linux.

* [Agenvoy v1.1.4](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.

* [Eve eve@0.73.0](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.

* [qm vendored-slack-socke...](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.

* [Eve eve@0.76.3](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.

* [Eve eve@0.76.2](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.

* [StepFun Harness v1.0.10](https://github.com/abbcreat-cyber/stepfun-harness) – Desktop AI workspace that provides Step Code-based execution, multi-agent workflows, plugins, and Step Plan APIs with OpenAI and Anthropic support.

* [StepFun Harness v1.0.9](https://github.com/abbcreat-cyber/stepfun-harness) – Desktop AI workspace that provides Step Code-based execution, multi-agent workflows, plugins, and Step Plan APIs with OpenAI and Anthropic support.

* [StepFun Harness v1.0.8](https://github.com/abbcreat-cyber/stepfun-harness) – Desktop AI workspace that provides Step Code-based execution, multi-agent workflows, plugins, and Step Plan APIs with OpenAI and Anthropic support.

* [StepFun Harness v1.0.7](https://github.com/abbcreat-cyber/stepfun-harness) – Desktop AI workspace that provides Step Code-based execution, multi-agent workflows, plugins, and Step Plan APIs with OpenAI and Anthropic support.

* [StepFun Harness v1.0.6](https://github.com/abbcreat-cyber/stepfun-harness) – Desktop AI workspace that provides Step Code-based execution, multi-agent workflows, plugins, and Step Plan APIs with OpenAI and Anthropic support.

* [StepFun Harness v1.0.5](https://github.com/abbcreat-cyber/stepfun-harness) – Desktop AI workspace that provides Step Code-based execution, multi-agent workflows, plugins, and Step Plan APIs with OpenAI and Anthropic support.

* [Eve eve@0.75.1](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.

* [Eve eve@0.71.3](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.

* [Eve eve@0.71.2](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.

* [Eve @eve/buzz-acp-adapte...](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.

* [Eve eve@0.71.3-tool-stub...](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.