Havuz

Can coding agents build the agent you actually want? A benchmark of 25 agent software engineering tasks across creation, editing and optimiz

A framework for discovering, compiling, and validating reusable skills for scientific agents.

十三希诺 Agent 工作流 · 中文源库：把工程纪律做成可机检门禁的元工作流 Skill 家族——三级跑道／判级／GATE 12 字段可复跑证据／405 条细则库／五包交付（核心+流程+角色+产品工程+单文件蒸馏），五平台注入适配。docs/ 为开发工作区，实验数据已归档。En

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

面向 LLM 交易 Agent 的抗污染回测、确定性回放与训练轨迹生成，支持 A 股研究｜Leakage-resistant backtesting, deterministic replay & training trajectory generation for LLM tr

Code repository for World Model From Scratch book

Pre-inference tool and agent routing for MCP, A2A and tool-rich LLM systems. Reduce candidate tools before model inference with policy-aware

Build & prompt Qwen3.x agents in their native dialect — extracted from qwen-code & Qwen-Agent

A minimal coding-agent harness built to measure what context management actually costs: constraint survival after compaction (8%→83%), def

Async Python bot that scrapes YouTube trends, analyzes viral strategies with Gemini LLM, and dispatches HTML reports to Telegram.

Framework for building continuous-loop autonomous AI agents.

Coding Agent Runtime & Evaluation Harness for controlled repository-level software repair

A pure-Python system that automatically discovers, verifies, and applies relevant historical requirements for coding agents — no embeddings,

Cost-efficient coding-agent runtime: prefix-aware prompt-cache routing, poisoning-safe semantic cache, budgeted context compression, request

Overnight experiment: can an AI agent make money, and can you trust what it reports? The agent produces claims; a separate verifier it canno

PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents

A skill library that teaches Claude Opus the working disciplines of Claude Fable 5. Move the checkpoints, not the capacity.

Make Claude Opus 4.8 behave like Claude Fable 5 — doctrine output style, drift-catching hooks, and an eval loop against golden Fable transcr

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

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

OpenCode agent configuration — a read-only orchestrator delegates to 6 specialized subagents. Expert model plans, fast models execute. Isola

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

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

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

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

Runtime security for AI agents. In-process, zero dependencies, Apache 2.0.

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

Human as Agent（人即智能体）· Human-as-LLM 人工代理网关：把工程师变成模型，OpenAI 兼容 /v1 接入 Agent 调度池，涉密/需人工任务路由给真实工程师。为 AI Agent 提效、为平台/运维收集工单。Human-as-LLM Gate

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

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

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-

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

Open-source agentic software development platform for building, orchestrating and monitoring autonomous AI coding agents.

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.

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

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.