Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it. Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 13 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

HEDGEHOG codes Cleaner, Faster and with Fewer Tokens. Hedgehog's AI-driven development builds a task dependency graph from your spec-driven, BMAD-METHOD plan, so Claude Code, Cursor & Gemini CLI stay locked to it. A CLI-enforced state machine for agentic coding. Now builds DeepSeek DSH Plugins. DeepSeek Harness、DSH 插件、AI 编程、BMAD 方法

The AI-coding operations layer that makes "done" require evidence — persistent memory, evidence-gated completion checks, and clean handoffs for any AI agent (Claude Code, Codex, Cursor). State lives as plain files in your repo. CLI + MCP, 0 runtime depend

Android Full-Stack Device Control Platform: WebRTC/H.264 remote desktop, UI/OCR/image-matching automation, one-click MITM, built-in Frida, proxy/VPN/frp/P2P networking, MCP/Agent, 160+ APIs, designed for multi-device clusters and engineered deployments.

A structural code search engine for Al agents.

📚 A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging experience. Python stdlib only. | https://misakanet.org

The Forge Skills Plugin bundles several Forge-focused skills plus MCP-backed tooling so your agent can scaffold apps, review them before deploy, debug production issues, and stay current on Forge APIs and the Atlassian Design System.

Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.

Open-source control plane for your AI agents. Connect tools, hire agents, track every token and dollar

Lint your AI agent context files, MCP server configs, and session data against your actual codebase

Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they touch, and proves what they save. 60–90% fewer tokens as the receipt. 76 MCP tools, 30+ agents, local-first.

Probe any ACP-compatible agent for its capabilities (models, modes, configOptions, prompt capabilities, auth methods, MCP transports). No real prompt required; no token cost.

DJ Claude — the only music MCP server with multi-agent collaboration

MCP (Model Context Protocol) server for Roblox Studio integration - enables AI coding agents to interact with Roblox Studio in real-time

One-command installer for all Windy Road AI agent plugins and skills

Open-source browser automation MCP server. Control your real Chrome from any AI agent.

The agentic harness for AI coding agents — work cycles, bounded RAG context, persistent memory, guardrails, and performance evals.

A native DeepSeek Harness (dsh) plugin bridging dsh coding agents to Feishu/Lark group chats — one group, one project directory.

Built by DeepSeek, for DeepSeek — a Swift-native macOS coding agent

A Pi productivity suite with Claude Code-style UI, context inspection, and agent/session references

Automated harness evolution for AI agents. A Claude Code plugin that iteratively optimizes system prompts, routing, retrieval, and orchestration code using full-trace counterfactual diagnosis. Based on Meta-Harness (Lee et al., 2026).

Brewcode - full-featured development platform for Claude Code: infinite focus tasks with automatic context handoff, prompt optimization, skill/agent creation, quorum code reviews, project rules management, and knowledge persistence

Coordinate AI coding agents in shared cubes. Works with Claude Code, Codex, and OpenCode.

Supercharge AI Agents, Safely