Havuz

My complete journey to becoming an Agentic AI Engineer through structured learning, projects, experiments, and production-ready implementati

A minimal, language-agnostic harness for Claude Code and AGENTS.md-compatible coding agents. | Claude Code와 AGENTS.md 호환 에이전트를 위한 미니멀·언어

Curated catalog of open, specialized AI agents for real business work — organized as broad umbrella categories (video, image, voice, SEO, so

Risk-first agent skill for PR/branch review: blast radius, agent-authored checks, call-graph pincer, structural bar.

Local-first, LLM-agnostic memory system — hybrid retrieval (vector + lexical + graph), multi-signal ranking. Runs on 4GB RAM, CPU-only, no c

Self-aware cognitive AI agent with a persistent soul: reads, modifies & verifies its own code, plans autonomously, dreams in idle time, reme

Forkable shell substrate for a single code repository — DB-backed identity, memory, roadmap, content; harness-agnostic boot. We build the da

A streaming action language for computer-use agents. LLMs emit one JSON action per line; the executor runs each the moment its newline arriv

A long-horizon CRPG benchmark for frontier agents. Raw 320x200 frames, Traditional Chinese, isometric navigation, twelve books to find.

Semantic UI automation and lightweight accessibility snapshots for LLM agents to interact with Web and Desktop applications.

No API keys required. Transform the native ChatGPT, Claude, and Gemini web interfaces into fully autonomous local coding agents.

A typed, replayable, budget-aware programming language for LLM agents. Compiles to Python & TypeScript.

🦴 paleo — token-saving skills for LLM agents: compress output, trim context, cap budget (Claude Code / Codex / Gemini / Hermes)

Browser-native multi-agent playground: drop LLM personas on a 3D map, watch them live, and talk to them. OpenAI, Gemini, Claude, Ollama. No

Verification-gated skill routing and self-improvement harness for Hermes-style agent skills

An end-to-end framework for Agentic Reinforcement Learning.

Run one AI agent as the orchestrator of your whole workspace, inside the Orca ADE, on the CLI subscription you already pay for. No API key,

Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.

Eval-driven multimodal agent for identifying trees, logs, bark, leaves and wood from photographs. Dendrology is the reference domain; the e

An MCP server built on top of Huawei Training Camp (HTC) APIs, enabling AI agents to access and analyze Huawei Health training data.

Per-step LLM routing benchmark with 970 static labels, live SWE-bench evaluation, an open data pipeline, and a public leaderboard.

Lossless context folding for the Pi coding agent: only the oldest context changes; the fresh window stays untouched.

Open-source, self-hosted AI employees that ask before they act. 46 business roles, approval-gated autonomy, untrusted-content safeguards, sa

Intent-bound action authorization for AI agents — deterministic, per-action approval a prompt injection can't re-point, with a signed, tampe

Hybrid vector + knowledge graph RAG system for enterprise documents. Fuses Pinecone dense vectors, BM25 sparse reranking, and Neo4j multi-ho

A phase-aware operating system for coding agents that helps them explore, ship, harden, and verify without losing the plot.

20 runnable LLM agent design patterns in Python, benchmarked, traced, offline-compatible. ReAct, multi-agent, constitutional AI, and more.

Zero-token long-term memory for Claude Code. Indexes your own session transcripts and retrieves evidence deterministically — entity-context

Companion repo for Agentic Graph RAG (O'Reilly, Anthony Alcaraz & Sam Julien) — 50 runnable skills + 8 pedagogical notebooks covering all ei

A local-first Windows AI assistant with a multi-model council pipeline, Python sandbox, web search, and cloud AI support. Free. Private. No

Supervisor/Lead/Peer governance for multi-agent coding — one policy core enforced identically on Pi and Claude Code, brief-scoped authority,

Research Pilot helps AI agents understand, maintain, and advance research projects through papers, claims, evidence, experiments, and human-

Give any AI agent its own disposable Linux machine. Firecracker microVM sandboxing with millisecond boot times, full network access, and nat

Production-ready Claude Code decision intelligence marketplace with adversarial routing, evidence-driven analysis, specialized agents, bench

Agent emotional continuity with PAD state, trust, appraisal, and compact emotion logs.

Run a flock of AI coding agents, each in its own git worktree, started by your ticket queue, merged by you. Work assigned to you in Jira, Li

Pier Code is a terminal-native agentic coding tool that understands your codebase and helps you move faster by handling routine tasks, expla

MCP server + CLI that lets Claude Code agents delegate tasks to agents in other project directories. Multi-agent orchestration: parallel dis

PTCG-Bench: Can LLM Agents Master Pokémon Trading Card Game? (EMNLP 2026 Findings)

Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.

A scientific-method lab notebook your AI agent drives — research as a tree of questions and falsifiable hypotheses in plain markdown, with a

EC2-Bench (EC²-Bench): benchmark for edge-cloud collaboration in long-horizon LLM agents — task performance, resource usage & privacy exposu

Train computer-use agents end-to-end on real desktops, at scale: a high-performance runtime where 8K+ live environments on one laptop thread

An Agent-native Obsidian wiki + CLAUDE.md skeleton that lets Agent know your project as well as you do.

Forge your own agent harness — a config-to-code generator that renders a thin, standalone Python agent harness you fully own. No LangChain/L

多功能 AI 编程助手 支持web/本地应用/bot接入 等

Autonomous pipeline that finds energy and CO₂ hotspots in any codebase and ships efficiency fixes proven by embedded statistical A/B testing

The agent that learns how you decide - and proves it by never deciding for you. A local-first, loop-native runtime for a team of AI agents o

Installable graph engineering for Claude Code, Codex, OpenCode, Cursor, and OpenClaw — dependency-graph execution with local caching, qualit

Run AI coding agents unattended for hours and ship PRs worth merging. Cybernetics-based multi-agent orchestration + cross-LLM peer review fo