Havuz

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

AI agent skills for thinking clearly, making better decisions, and getting things done. Strategy, research, decision-making, planning, risk

Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction

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

Writ: An AI agent skill that catches AI writing tells and clichés using a self-edit checklist drawn from Wikipedia's Signs of AI Writing gui

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

The agent that evolves with you 𖤍

STEER — AI4R (AI for Research) experiment framework for auto-research and autonomous research. Connect existing research projects and let an

Decision provenance and data-flow tracking for coding agents: computes what changed in your code and data, records why it changed, and surfa

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

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

A sandbox service for running untrusted, agent-authored code that reports the isolation boundary each run executed behind. Lessons, no clone

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

Multi-agent demo for Statewave conflict resolution. Concurrent agents write to a shared subject; the compiler detects contradicting facts vi

Automate web workflows on real browser tabs without hosting a browser farm.

Token-efficient CLI for Atlassian Server/DC (Jira, Confluence, Bitbucket) — drop-in alternative to mcp-atlassian for LLM agents. Compact out

Skill pack that turns any coding agent (Claude Code, Codex, AGENTS.md-compatible) into a senior production engineer — FastAPI, PostgreSQL, D

Персональна база знань, що наповнюється та структурується за допомогою LLM-агентів. Проєкт побудовано на патерні LLM Wiki, створеному Андре

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

Model-agnostic output control for LLM agents: concise, action-first answers with proof and risk preserved. Native install paths for Claude C

An audit agent that proves whether a person's data is really gone: resolves identity across systems, judges state at the audit cutoff, finds

The agent loop for Python. Your harness, any model.

F.R.I.D.A.Y — a secure self-improving personal AI agent. Local-first, with memory, tools, voice, MCP, automation, and verified self-extensio

FastAPI reference app for Statewave memory integration. Wraps every chat turn with get_context before the LLM call and record_episode after;

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.

AgentBehaviorBench (ABB): A benchmark for evaluating AI agents’ ability to test other agents and detect behavioral defects.

AI for tactical cycling intelligence: Predictive mud logic, S-Scale terrain analysis, and powered GPX routing

The control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into

多功能 AI 编程助手 支持web/本地应用/bot接入 等

SWE-Serve: an agentic benchmark of 53 production inference-engineering tasks derived from merged SGLang pull requests, run with Harbor.

PikoClaw - Born from the Claude Code leak, a lightweight, Rust-based AI agent engineered for high-performance development

A recursive self-improvement (RSI) workflow that evolves both target agents (e.g., Pi and DeepSeek Harness) and the RSI system itself.

Autonomous AI research harness for Claude Code. Sibling to rockie-codex (OpenAI Codex CLI). Apache-2.0.

LLM agents that write machine-checked cryptographic proofs in EasyCrypt (arXiv:2607.02847)

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

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.