Autonomous, self-improving AI agent platform for Claude Code — safe capability & skill acquisition, MCP/tool discovery, sandboxed policy gates, and token-efficient learning.

Global persistent memory for OPENCODE sessions. Inspired by Claude Code's auto-memory — your agent remembers what it learns, across every session, globally.

531 searchable AI Agent Skills for Claude Code, OpenAI Codex, and OpenCode — EN/TR catalog, platform and risk notes, direct ZIPs, and curated bundles.

Bilingual, searchable Agent Skills for reproducible scientific research across Claude Code, OpenAI Codex, and OpenCode.

Opinionated workstation setup for Apple Silicon macOS and Debian or Ubuntu desktops.

The agent context layer — converge messy multi-session AI-agent work into one lean, LIVING, spec-centered source of truth that doesn't rot. Organize docs by lifetime, keep the spec generative, and let an agent (or a human three months later) build from it.

Shareable A.I.M. agent skills library — install into agy/grok/opencode. Own your stack.

Evidence-driven engineering harness for autonomous coding agents

A Claude Code skill that curates your auto-memory store — pruning and sharpening it, not just growing it.

Diagnosis-free neurodivergent support skills for AI coding agents, with executive-function scaffolds and always-on Claude/Codex behaviors.

Converts plain markdown into OKF-conformant knowledge bundles

Reusable repository guidance, workflows, runbooks, and skills for people, Codex, and Claude Code.

How I work, encoded as skills — 88 portable AI SKILL.md files (research, design, AI-product, motion, code, business). Fork it, make it yours. Inspired by @mattpocock + @emilkowalski, grounded in NN/g.

268 AI coding assistant skills, organized across 12 workflow layers. Sources include Anthropic official, FRM, SKC, LRN, SKA, and other mainstream AI coding frameworks.

Identity, memory, trust, and swarm primitives for AI agents. MIRC base always free.

Analytical memory for AI agents: a real Postgres queried in plain English over MCP. One command.

Local-first agent memory: versioned JSON categories, BM25 search, per-device ACL, fleet sync.

Efficient context management: code search, evidence packs, and memory for coding agents.

Local-first graph memory for AI assistants with SQLite, semantic search, and MCP tools.

AI memory buyer routing with Forge docs, pricing, paid recommendations, and MCP discovery.

Persistent memory for AI agents - hybrid semantic + keyword recall with autonomous consolidation

Persistent memory for AI assistants. Store, search, and recall across sessions.

Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token.

Persistent memory layer for AI coding agents — your agent remembers what you taught it.

CognOS trust scoring (C=p·(1-Ue-Ua)) and session trace storage as MCP tools.

Stale-proof repository memory with citations + just-in-time verification + TTL (repo-scoped).

Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.

Persistent coding memory for AI assistants. MCP stdio, hybrid search, graph, context.

Persistent memory for AI agents. Remember, recall, and explore a shared knowledge graph.

Local-first memory system for AI agents with hybrid search and graph reasoning

AI long-term memory MCP server with importance scoring and confidence calibration

Markdown memory for AI agents. Files you can read, edit, grep, and commit. Not a database.

Shared, git-tracked working memory for AI agents on the same codebase.

Back up and migrate your Claude Code setup (~/.claude) safely across machines and accounts. Cross-platform, pure Python stdlib, MIT licensed.

Codex and Claude Code skill for agent-maintained project wikis, layered code indexes, and low-token repo navigation.

AI utils & skills

AI utils & skills

AI utils & skills

Personal collection of reusable Claude Code agentic skills, packaged as an installable plugin marketplace.

Custom Claude Code skills for session handoff, verification, planning, research, audits, and decision-gathering.

Per-repo session memory for Claude Code: a NOW.md + daily journals that survive across sessions. Files are earned, not scaffolded.

🚀 Evidence-driven context engineering for AI agents coding

Early Modern English mode for Claude Code, Codex CLI, and GitHub Copilot. Wastes tokens beautifully.

A Claude skill that gives your projects persistent memory — interview-based kickoff with auto-tracked decisions and progress.

A collection of Claude Code plugins for Terraform provider development.

個人 Claude Code plugin marketplace：skill 管理指令（skill-list/status/RCM）＋ commands-only 的 ponytail。

Claude Code skills for using AI agents to develop and maintain large, long-lived codebases across sessions: AGENTS.md/CLAUDE.md layered conventions + auto session-notes hook.

Claude Code skills for using AI agents to develop and maintain large, long-lived codebases across sessions: AGENTS.md/CLAUDE.md layered conventions + auto session-notes hook.

Claude Code skills for using AI agents to develop and maintain large, long-lived codebases across sessions: AGENTS.md/CLAUDE.md layered conventions + auto session-notes hook.

Claude Code skills built while shipping real client websites — image generation without API keys, per-project memory, evidence-producing QA.

Agent Skills for software distribution — apt-setup (Debian/Ubuntu) and choco-setup (Windows), SKILL.md standard

Two free Claude Code skills for the boring parts of shipping software — PR description writer & CLAUDE.md tuner. Free tier of the Deckhand pack.

Extract Claude Code skills from AI workflow YouTube transcripts. 10 ready-to-use skills + a meta-skill that automates the extraction process. Built from John Kim's 50 Claude Code tips.

10 Claude Code skills for compound engineering workflows — session discipline, harness auditing, phase governance, and issue pipeline

10 Claude Code skills for compound engineering workflows — session discipline, harness auditing, phase governance, and issue pipeline

10 Claude Code skills for compound engineering workflows — session discipline, harness auditing, phase governance, and issue pipeline

10 Claude Code skills for compound engineering workflows — session discipline, harness auditing, phase governance, and issue pipeline

🤖 My Claude Code config!

Dev-focused Claude Code harness — workflow-engine skills, in-repo memory, session continuity (/recall ↔ /vault-push), local telemetry, + a ready-to-fill vault scaffold. clone + ./install.sh and go.