| 09/12 | 9 |
AI-powered CLI that reviews Git diffs using LLM agents and deterministic pipelines to produce precise, line-level structured comments.
|
| 10/09 | 8 |
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.
|
| 10/10 | 7 |
Go-based AI agent framework with self-improving error memory, multi-provider LLM routing, script/HTTP tool extensions, and OS-native sandboxing.
|
| 10/02 | 7 |
Multiplayer agent harness that provides isolated per-user workspaces with scoped memory, files, permissions, and background tasks across Slack and the web.
|
| 10/09 | 6 |
Filesystem-first framework for building durable AI agents, placing core capabilities in conventional directories for easy inspection, extension, and operation.
|
| 10/08 | 6 |
Codex Desktop-style coding harness that provides a host runtime and protocol core across Windows, macOS, and Linux.
|
| 10/02 | 6 |
Hermes-style persistent memory extension for Pi coding agents with session search, learning from failures, secret scanning, and reusable procedural skills.
|
| 10/01 | 6 |
Local desktop harness that runs Claude Code terminals as collaborating autonomous agents with shared memory and a GOD orchestrator.
|
| 10/01 | 6 |
Multi-agent harness that turns terminal coding CLIs into a coordinated team running locally on your machine with long-term memory and agent routing.
|
| 09/19 | 6 |
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.
|
| 09/13 | 6 |
One-click Electron desktop companion for DeepSeek Harness, providing an AI agent and GenUI-based web interface on macOS and Windows.
|
| 10/10 | 5 |
Desktop AI workspace that provides Step Code-based execution, multi-agent workflows, plugins, and Step Plan APIs with OpenAI and Anthropic support.
|
| 09/12 | 3 |
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.
|