MCP servers and skills: search, filter by where they run, and compare.
Long-horizon context window compression and semantic deduplicator eliminating redundant tool outputs
SkillLink only★ 7
Long-horizon context window compression and semantic deduplicator eliminating redundant tool outputs
SkillLink only★ 7
What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center
SkillMIT★ 711No key
Simple, organic, lightweight yet purposeful memory system for Claude Code.
SkillMIT★ 49No key
Autonomous multi-batch development skill for Claude Code and Codex. They work while you sleep.
SkillMIT★ 221No key
Claude Code skill for recursive research up to PhD level across any domain. Source tiering, WDM + Munger inversion for autonomous decisions, and disk checkpointing to survive context compaction.
SkillMIT★ 52No key
The visual Kanban for long-running AI agents. Watch your agent's plan organize itself: dependencies unlock into Ready, the critical path lights up, the one next move is obvious. Nobody wants to read a
SkillMIT★ 68No key
A dependency-free bootloader that reloads project AGENTS.md after context compaction across AI agent harnesses—automatically, visibly, and fail-closed.
SkillMIT★ 1Few starsNo key
Progressive Skill Disclosure & Context Compaction Engine for Autonomous AI Coding Agents. Reduces prompt token bloat by 96.7% using JIT discovery, ephemeral schema injection, and semantic receipts.
SkillApache-2.0★ 3Few starsNo key
Universal long-term project memory for AI coding agents — Claude Code, Cursor, Windsurf, Cline + 4 more. TDD rules, code graph, spec-driven dev, cross-session recall.
SkillMIT★ 31No key
Open-source Codex skill for keeping long-running tasks aligned across context compaction, corrections, and resumed work.
SkillMITFew starsNo key
Open-source agent skills for Claude Code, Codex and OpenClaw. Every skill ships with receipts. #01: compact-receipts — what your last context compaction dropped.
SkillMITFew starsNo key
A reverse engineering and CTF agent for the terminal: planner/executor/researcher routing, 24 local tools, workflow modes, and live turn visibility.
SkillMIT★ 5No key
Claude Code session handoffs — now a Claude Code mod: /compact-handoff swaps the conversation for a validated handoff and keeps going. Skills + chain-linked sessions.
SkillMIT★ 67No key
Lightweight research checkpoint and session recovery protocol for Codex agents. Preserve scientific decisions, experiment evidence, and Git state across context compaction.
SkillMITFew starsNo key
五种载体，一座本地对话档案馆：原文归档、分层后台摘要、原文查证与跨工具接续。默认原生压缩，Claude Code 与 dsh harness 可选接管。Local archive, layered summaries and exact-source recall across five harnesses; native compaction by default.
SkillMIT★ 3Few starsNo key
Persistent persona memory for Claude Code, Cursor, Codex, Copilot, Antigravity. Mesh-structured state survives context compaction. Project-isolated.
SkillMITFew starsNo key
Context-Driven Development toolkit for AI agents — spec-first planning, TDD workflow, and Beads integration.
SkillApache-2.0★ 19No key
Context health watchdog and verified session handoffs for Claude Code and Codex
SkillMIT★ 1Few starsNo key
A Go-based agentic framework for building highly-scalable, durable AI agents with first-class persistence, observability, and CLI tooling.
SkillMIT★ 5No key
A lightweight project-management layer that sits above OpenSpec and Superpowers — tracks epics, an explicit detour stack, and a reconcile gate so nothing is lost across pivots or context compaction.
SkillMIT★ 1Few starsNo key
Orchestrator skill for crafting context-rich GitHub issues and PRs. Inspired by deepwork+oracle, homedir, Herne, and Kimi CLI compaction. Includes caveman extreme-compression mode.
SkillMIT★ 2Few starsNo key
A complete, opinionated Claude Code configuration with global instructions, 20 slash commands, and sensible defaults.
SkillMIT★ 5No key
Who stands behind it
