— · MIT
massa-ai plugin for Claude Code — semantic code search, durable memory, symbol graph, and context compression
v1.0.1 · MIT
Topic-based automatic memory for Claude Code — never lose context across sessions or compactions.
— · MIT
Claude Code skill for handling long-context tasks through recursive decomposition
— · Apache-2.0
Local-first MCP server that gives coding agents structured context packets, code/schema facts, and diagnostics - backed by a local SQLite store.
— · MIT
Unofficial community workarounds for Claude Code (empty thinking summaries; missing context-usage icon; no copy/paste of markdown).
— · no license
Give your Claude Code Agent Teams a memory. Auto-injects role-specific context into every new teammate — your team never starts blind again.
— · MIT
Autonomous session memory for Claude Code. Never lose context, never repeat yourself. AI-powered summaries, searchable history, and automatic context injection. 📦 npm install -g memctx
— · MIT
GSD Pro — The most powerful AI coding workflow for Claude Code. Free alternative to Cursor Composer, Copilot Workspace, Devin & Bolt. Multi-model routing, rollback/recovery, adaptive context. Fork of 30K★ original. npx get-shit-done-cc
— · MIT
Audit MCP servers, skills, and CLAUDE.md bloat eating your Claude Code context window.
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
— · MIT
Local-first, agent-native control plane for ComfyUI — MCP server + autonomous sidebar agent that drives your live graph in natural language on ANY LLM: Claude/ChatGPT/Gemini on your subscription (no API key), free local models via Ollama (fully offline),
v0.4.0 · MIT
Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code durable memory — entirely offline.
v2.3.0 · Apache-2.0
Add MCP servers to your favorite coding agents with a single command.
— · Apache-2.0
Persistent memory for AI coding agents, powered by iii-engine's three primitives
v2.2.0 · MIT
Mechanical plan/dev/self-audit/external-audit gates for AI coding agents, with a configurable role-routing topology engine, an MCP-UI live status panel, and native-tooling Claude Code V2 dispatch. Claude Code, Codex, OpenClaw, and PyPI.
v0.49.0 · MIT OR Apache-2.0
Linter for AI agent configurations. Validates SKILL.md, CLAUDE.md, hooks, MCP, and more.
— · AGPL-3.0
The agentic workspace where people and agents work together in the loop.
v0.6.0 · MIT
Domscribe is a pixel-to-code development tool that bridges the gap between running web applications and their source code.
— · MIT
The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 9 agents · 16 skills · 4 workflows. Fail-closed gates, test honesty, anti-anchored review.
v0.61.0 · MIT
Workflow control for AI coding agents
v2.7.2 · Apache-2.0
Content-aware output compression for AI coding assistants. 36 specialized processors cut CLI output tokens by 60-99% (git, pytest, npm, terraform, kubectl, docker, and more) without losing errors, diffs, or stack traces.
v7.66.0 · MIT
Run Claude Code with any model - OpenRouter, Ollama, LM Studio & local models
— · Apache-2.0
Self improving agents through iterations
v2.0.0 · MIT
Install engineering discipline into any AI coding assistant. Composable skills for design, implementation, review, and team standards. Better process, not just better prompts.