Havuz

HOP 3.0 — HopSpec task-spec language + HopJIT execution engine for LLM agents

Portable AI memory powered by knowledge graphs. Transform conversations into a persistent, explorable knowledge graph and give any LLM long-

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

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

Asking for What Was Never Requested: horizontal and vertical proactivity in LLM agents. Need-graph metrics (no LLM judge) and Q&D, which tra

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

Claude Code skill + 18 AI agents for Android & iOS mobile app security audits. OWASP MASVS/MASTG-aligned, with adversarial exploitation conf

Open-source Android assistant that replaces Gemini. Summon it by gesture, bring your own API key, and it reads the screen, taps through apps

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

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

SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation

Local-first Agent RL workbench for Search-R1 rollouts, reward evaluation, GRPO/verl training-data handoff, and an auxiliary private RAG work

5-agent AI team for Claude Code operators: Iris (design), Lyra (build), Echo (scout), Newton (research), Hypatia (critic). One-command insta

Evidence-backed audits, evaluations, and measured improvements for any AI agent.

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

Personal collection of Agent Skills for AI coding agents (Claude Code, Gemini CLI, Cursor, Codex, etc.)

A React + TypeScript spatial canvas and node-board library for whiteboards, visual editors, and graph interfaces.

ALGAL is a programming language for agents. Programs pause for approvals, survive restarts, replay from recorded effects, and improve throug

Helix is ​​a powerful self-learning AI agent with memory, skills, and the ability to recall tools. It learns from successful tasks and creat

Reusable AI skills for Codex, Claude Code & Copilot CLI — Markdown-only, safety-first samples for diagnosing bugs, drafting changelogs, and

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

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

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

DrugTargetWorld: a synthetic biobank for training and benchmarking AI scientists on end-to-end drug target discovery. Paper: arXiv:2610.0955

The control layer for agentic AI. A protocol-aware proxy that applies identity, policy, trust and payment controls to A2A, MCP and DIDComm t

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,

神经元记忆网络 让 DSH 记住「为什么这么决定」，而不只是结论。思维链记忆插件：8 个池分级遗忘、每轮注入、神经元 3D 星云浏览、夜巡自动整理。

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

Manipulation benchmarks test acting to change; EmbodiedLab tests acting to know. Given only an objective and the apparatus, a robot runs its

Adversarial LLM Reversal for hermes-agent

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

An agentic LLM-powered knowledge assistant that enhances RAG capabilities through automated entity extraction, structured data analysis, and

Gates 84.7% of tool-schema prompt tokens away for DeepSeek Harness: plugins declare themselves organs, a nerve impulse routes each command,

Local desktop coding assistant you can run with any local model. No API key required. It can read your project, edit files, run commands, ve

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

An autonomous agentic pipeline that finds, proves, and patches real C memory-safety vulnerabilities end-to-end using a single 7B open-source

Open source release of Data Science Agents that can analyze and transform datasets as well as train and infer models to augment your data sc

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

EMNLP 2026 Industry Track | A benchmark for shopping agents on long-horizon tasks with distributed hidden intent.

Profine automatically profiles and optimizes PyTorch training jobs on real GPUs, delivering measurable speedups and lower GPU costs before t

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

A Codex CLI plugin packaging a full software studio — 45 specialist roles, 91 workflow skills, and deterministic quality gates for game and

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

针对中文AI编程的Top 20 提示词，做skill用于辅助codex/claude生成代码

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

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

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

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

OR-Space: a full-lifecycle workspace benchmark for industrial optimization agents