v0.1.1-rc.2 · MIT
DeepSeek Harness: Everything is a Plugin.
v4.9.0 · MIT
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
v1.5.23 · MIT
The open agent skills ecosystem
v4.0.3 · Apache-2.0
Trigger.dev – build and deploy fully‑managed AI agents and workflows
v2.5.0 · MIT
Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code
v9.66.1 · MIT
Run multiple AI models against the same research, design, or coding task. Surface disagreements before you ship.
v2.5.0 · MIT
Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear
— · MIT
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
v0.7.148 · Apache-2.0
Hivemind turns your traces into reusable skills across agents
v13.15.3 · Apache-2.0
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
— · Apache-2.0
Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.
v2.1.2 · MIT
The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches
v4.23.1 · Apache-2.0
Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, and messages.
v1.8.6 · Apache-2.0
The missing open-source Kubernetes UI with a built-in MCP server for AI agents. See what's broken, why, and what changed. Issues, Topology, event timeline, Helm, GitOps, live service traffic, and cluster audits - all in one Go binary.
v1.3.5 · MIT
The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets.
v2.4.0 · MIT
通过扫码或机器人凭据把IM机器人接入DeepSeek Harness(支持飞书、微信、钉钉、企业微信、QQ、Slack、Telegram、Discord和WhatsApp)。 Connect IM bots to DeepSeek Harness via QR code or credentials (9 channels).
v2.9.4 · MIT
A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.
v0.4.0 · MIT
Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code durable memory — entirely offline.
v2.4.0 · AGPL-3.0
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.
— · MIT
Development workflows for Claude Code that keep broad exploration focused on the outcome you approved.
v2.3.0 · Apache-2.0
Add MCP servers to your favorite coding agents with a single command.
v2026.8.6 · MIT
Claude Code plugin that asks several AI coding agents the same question and shows their answers side by side. Gemini, OpenAI, Grok, Perplexity and Kimi over API; codex, antigravity, grok and kimi CLIs on subscription auth; ollama locally.
— · MIT
Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute with automatic verification, review with 4-agent parallel audits, and capture learnings as reusable knowledge.
— · MIT
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow.