Havuz

AI-powered SAST scanner that finds auth bypass, IDOR, and logic bugs Semgrep/CodeQL miss. Free GitHub Action. Supports Python, JS/TS, Go, PH

Ultra-Sparse Adaptation of 1-Bit LLMs via XOR Patches

Building a small LLM in PyTorch from scratch - a step-by-step journey inspired by Stanford CS336.

Yosuri — LESS CHAT, MORE AUTOMATIC. A 24H self-evolving AI agent that aggregates free models into one OpenAI & Anthropic-compatible API, pic

🧭 给 Claude Code / Cursor / Codex 用的『架构副驾』skill —— 开新项目时用持续深度提问引导你在写代码前想清楚架构(产出架构图 / ADR / 演进路线)。知识源自 awesome-architecture。中英双语。

AI-powered repository agent for GitHub, GitLab, Gitea, Azure DevOps. Issue triage, PR analysis, merge queue, notifications, dashboard, backu

grok-build with the leash off — one binary, any OpenAI-compatible endpoint, zero phone-home. No x.ai account.

⚡ Ultra-Reliable AI Inference Gateway & Verifiable Agent Control Plane. Dual-Dispatch, Zero-Token JSON Auto-Healer, VaaS On-Chain Attestatio

Convert CodeBuddy/WorkBuddy (Tencent coding assistant) subscription into an OpenAI-compatible API. Use CodeBuddy GLM-5.2/Kimi/DeepSeek model

Nuphus — 本地优先的 AI Agent：真实桌面执行力 + 手机第二块屏幕。Local-first AI agent with real desktop execution and dual-device real-time sync.

An AI workforce platform: role-specialized agents with multi-provider LLM, MCP, tasks, and a web + CLI UI. You're in charge.

SDKs and reference implementations for the Synadia Agent Protocol for NATS

Coding agent orchestration for engineering teams — shipped as a spec plus a working reference implementation.

Persona agents with explicit memory, retrieval, adversarial smoke tests and a practical post-training roadmap.

A local CLI, built on ccusage, that syncs your token usage with everyone else.

Ask your house a question, get a number back. Home Assistant integration for TypeSafe Jev: typed answers as sensors, four actions for automa

A minimal local coding agent in Go — a faithful port of Sebastian Raschka's mini-coding-agent, with no LLM framework.

This web browser has been designed to help your agent debug and develop complex web applications. (MCP Server)

学习 learn-claude-code 后的 PR Review Agent 实践项目：构建 Debate Council 多 Agent 审查、Tool Calling、结构化报告与 AI Judge 评估。

CubeLoop — a Pythonic, async-native agent harness core designed for high performance, readability, and production-grade persistence.

Give every agent your team's brain on day one. The memory layer for AI agents. Everything your team knows. Cited, and always up to date.

NEURA Office: native Word, PowerPoint and Excel for Open WebUI. LibreOffice-compatible OOXML. MS365 assistant planned.

Find and redact secrets in AI coding agent histories (Claude Code, and more).

A pure-Go port of pi (earendil-works/pi) — the pi-ai unified multi-provider LLM API, pi-agent-core agent loop, and pi-coding-agent, native i

The Distillery. A Token Optimization Proxy

EurekAgent: an autonomous research system for metric-driven tasks, built with Claude Code. Define the problem and metric. Get breakthrough r

Learn AI agents from first principles to production. Zero mandatory dependencies, pure standard Python 3.11+, and no magic frameworks.

The durable runtime for AI agents: event-sourced sessions, approvals that persist across processes, exact resume after a crash. A 2,200-line

Fine-grained robot control with Jev, physics previews, and configurable LIBERO tasks.

GNAP — Git-Native Agent Protocol. RFC Draft for git-based agent orchestration. Zero servers.

中国市场优先的 GEO(生成式引擎优化)+ SEO 内容优化系统:让内容被豆包/千问/DeepSeek/文心/元宝/ChatGPT/Perplexity 引用。兼容 Claude Code/Codex/OpenClaw/Hermes,零依赖,MIT。

Self-hosted AI coding agent with desktop & mobile UI

Don't make LLMs honest. Make every factual claim auditable. — An LLM Claim Auditing Layer with T1-T7 truth gradients. 98.1% business effecti

多智能体 LLM 股票/加密交易决策台 —— 13 位 AI 分析师研究、辩论、风控压测,收敛出可追溯、可实时观看的交易决策。 | Multi-agent LLM trading desk: 13 AI analysts research, debate & stress-tes

An open standard for portable, interoperable AI memory across tools, sessions, and devices.

AI Company로 자동화 조직을 만드세요

JDF — a JSON document format. Renders like PDF, diffs in git, edits in any text editor, reads natively for LLMs. Desktop Reader, jdf.js web

EduAgent: Open-Source RAG AI Tutor for K-9 Education. 国内首个专为1-9年级量身定制的开源 RAG AI 教辅智能体

数模Agent（数模 Agent）/ 数学建模 AI 助手：多智能体协作完成题意分析、文献检索、建模、代码执行与论文写作，支持人工审核和断点恢复。Local-first multi-agent workbench for mathematical modeling.

1Panel AI 网关提供从统一接入、智能路由到合规审计的全链条管控，让企业 AI 落地更安全、更高效、更可控。

[NeurIPS 2026] MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare.

A tiny Claude Code skill that keeps your prompt cache warm during idle sessions, so your next message reads from cache instead of paying ful

English text humanizer for Claude: typography, vocabulary, structure. Calibrates to your voice. Built on the UMD / Google DeepMind study and

The open archive of how AI agents actually work. A versioned, verifiable archive of system prompts, developer instructions, tool schemas an

Graphon is a Python graph execution engine for agentic AI workflows.

A finite ontology of 115 recurring software elements and a composition framework for LLM-based coding agents

This repository provides a starter kit for sports intelligence built on NVIDIA AI stack: playbooks, training recipes, and inference for Mult

Open-source, self-hostable social listening.

First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression wit

Open-source local-first cognitive memory. AGM-compliant belief revision (49/49 postulates). When a fact changes, downstream beliefs are auto