Code agents

Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.

Govern your documents like code. MCP server that indexes .md/.docx/.html/.pdf into a SQLite knowledge graph and runs drift audits — stale policies, conflicting research claims, superseded docs, undocumented code exports. 12 MCP tools incl. cross-reference graph, governance + provenance metadata, topic similarity. Single binary, zero runtime deps.

Local-first cross-corpus retrieval MCP server — model2vec embeddings + LanceDB (Tantivy BM25) + SQLite. One binary; hybrid (dense + BM25) search across markdown, code, and Claude Code sessions.

transformers safetensors qwen3_5_moe image-text-to-text code agent

Vendor-neutral continuation protocol for AI coding agents. Plain-file project state, stdlib validation, recovery and cold-agent handoff.

A.I.M. – Actual Intelligent Memory: zero-token exoskeleton for long-running Claude/Gemini/Codex CLI agents. External SQLite memory, GitOps guardrails, DataJack cartridges. Alpha, trenches-first.

Reusable AI agent skill for safe Proxmox homelab production operations, LXC activity logging, backups, security, and migration runbooks.

Sovereign AI coding agent for your terminal

Cross-tool plugin marketplace for deepagents-code (dcode), Claude Code, and OpenAI Codex — LangChain & LangSmith skills and MCP servers

JiuZhang · ALGOR — a local multi-agent quant research terminal for A-share investors. 多智能体量化投研平台。

A plan-driven, multi-agent coding loop: separate planner, coder, and reviewer roles, each on the provider and model you choose, work together to implement your plan.

Active state management for multi-agent coding — one versioned project brain (brain.klypix) over MCP

🚢 A crew of IDE agnostic sub-agents, slash-command workflows and tools that drive a GitHub issue from open to a reviewed, CI-green pull request — autonomously. Flagship: /ship-issue.

A Herdr-first captain/worker workflow for Hermes, Codex, Grok, OpenCode, Cline, Buzz, and other coding agents.

A declarative language that compiles to professional SVG floor plans — like Typst/LaTeX, but for architecture. Built for AI agents: deterministic output, JSON diagnostics that carry their own fix, and a describe/lint channel that verifies a plan against its brief without rendering an image. Zero-dependency TypeScript.

CLI for Model Context Protocol (MCP) servers. Pipe, script and automate MCP tools from the Unix shell, and keep their tool schemas out of your LLM context.

Context before response. Local, reviewable AI behavior calibration.

璇玑 Xuanji —— Go 单二进制 AI 网关，OpenAI / Anthropic 双协议汇聚。one-api / new-api / LiteLLM 轻量替代品，自动分流、负载、重试，成本优先路由，高可用不中断。

Community skills for Claude Code: token optimization, productivity workflows, and development best practices. All skills tested with TDD methodology (RED-GREEN-REFACTOR). Features rescue-tokens skill: 90% verbosity reduction, eliminates rate limits through 9 optimization patterns.

Self-hosted AI gateway. Route, translate and track requests across providers, with access keys, budgets, and a built-in dashboard.

Model Context Protocol servers for the official Robinhood Crypto Trading API — the credentialed brokerage API at trading.robinhood.com, documented at docs.robinhood.com/crypto/trading.

Claude Code пишет документацию по одному стандарту во всех проектах: скилл-диспетчер четырёх жанров, два агента, линт без токенов и хуки, которые включают всё это сами. Установка одной командой в ~/.claude

🪒 YAGNI enforcement at the harness level, nudges toward the simplest solution and gates against unnecessary dependencies, file sprawl, and unchecked build growth.

Publish, share and comment on the HTML and Markdown your coding agent writes. Self-hosted.

Orchestrator, reusable multi-agent workflows and observable, attachable sub-agents for the Pi coding agent.

🤔 aiduMEM — Memory & Thought Engine for AI Agents. Built on mem0. Ebbinghaus decay, hybrid recall, relevance gate, federated multi-agent memory.

Free & open-source MISRA C / CERT C / BARR-C compliance for embedded C — the vendor-neutral alternative to Polyspace, Helix QAC & Coverity's paid workflow. Agentic fix loop + MISRA Compliance:2020 audit evidence, from any IDE via MCP.

Not a chatbot. Not a coding assistant. A digital operator that controls your entire PC — 219 tools, screen perception, HID control, browser automation, Office suite, AI media. One sentence in, finished work out.

Open-source API to convert URLs and documents into PDFs, screenshots, Markdown, and structured data.

Agentic coding inside Visual Studio — Claude Code with a rich chat pane, an interactive terminal, and the IDE (editor, solution, debugger) exposed to the agent over MCP.

mlx gguf claude-code coding-agent tool-calling qwen3.5

"Educational tool for inspecting Claude Code ↔ LLM communication via hooks and proxy

This guide defines how we plan, build, review, and release software in an agentic-first engineering organization.

Pure-Python AI coding agent powered by DeepSeek V4 - Subagent-First architecture · Context is Currency · Terminal-native - Can connect Ollama models for Vision support - Uses the native web search built into DS v4 API and is built around the DeepSeek caching mechanism

A local AI research assistant with streaming chat, Hybrid RAG, and document search.

The structurally-verified context layer for AI coding agents. Cut 50-90% of your agent's token spend.

TrustOS is an AI Permission Layer that sits between AI agents and real-world actions.

Cut your Claude API bill: local proxy that auto-routes every request to right model. Zero code changes.

養成型 AI 伴侶框架｜Raise an AI companion who remembers, reflects, and grows with you.

Personal Claude Code skills, installable as a plugin marketplace

Long-term memory for Claude Code — a milestone-triggered, in-session work diary in plain markdown. No database, no lock-in, fully greppable.

The knowledge graph for APIs your agent can trust. Maps any API — even messy, paywalled, or on-chain ones — into a verified graph your agent traverses instead of guessing, and simulates any action to a receipt before money moves.

AI testing agent for pull requests: maps the blast radius of a diff, runs only the tests that cover it, drafts the ones that are missing, and gates the merge on a score. Plain-English YAML, no selectors. Local-first, BYOK.

面向 AI Agent 的规范化开发 Skill，帮助构建高质量智能体 | A structured skill for building reliable AI agents with specifications, workflows, and acceptance.

76 AI-agent security skills for Kali Linux tools — pentest, red team, forensics, OSINT, and more. Machine-readable skill definitions by Red Hound InfoSec.

Stateful execution layer for browser agents.

A Markdown-based operating system for diagnosing, designing, costing, building, and operating multi-agent AI systems. Methodology upstream of code.

AI 寫作痕跡清除技能，台灣在地強化版。涵蓋 46 種模式，包括中國用語偵測、中文標點保護、語域對照，可用於任何支援 skill 的 agent。

Run Claude Code on an unrooted Android phone via Termux + proot-Ubuntu, with free model access through a local 9Router proxy.

Cut the cognitive overload of orchestrating many Claude Code agents: a tiny desk device (Arduino + OLED, macOS) that shows which session needs you and jumps you to it. Personal/non-commercial (CC BY-NC 4.0). ESP32 Wi-Fi remote next.

SOC agent that ingests security logs, detects attacks mapped to MITRE ATT&CK, and uses an LLM grounded in a RAG knowledge base to analyze and recommend remediation, with human approval and rollback built in. FastAPI/Postgres backend, React frontend. Runs fully offline, no API keys needed.

Modular engineering methodology framework for AI agents — reverse engineering & software development (core + re-binary / re-code / swe modules).

Spec-driven iOS/macOS app development for Claude Code — from idea to App Store via /apple:* commands, specialist agents, and optional App Store Connect automation.

PaperCraft — From idea to accepted paper at top CS conferences. 17 rules + 12 skills that guide CS researchers through the full research pipeline.

Autonomous AI agent & benchmarking CLI for Claude Code and Cursor. Build, validate, and ship research hypotheses repos — entirely locally.

A virtual software company for Claude Code: 19 agents, 38 workflows, 16 quality gates. Takes an application project from idea to release.

Adeorq: nine agents working, one screen. A Windows and Linux desktop panel that runs AI coding agents in real terminals. Source visible, proprietary licence.

Tauri desktop GUI to manage Codex multi-agent bindings, orchestration and token usage without hand-editing TOML configs

A deliberately small Codex subagent team optimized for simple, long-lived, robust, elegant engineering without over-design.

Apple-native cloud-hybrid RAG client for PDFs and personal files using SwiftUI, Vision OCR, OpenAI embeddings and Responses API, and Pinecone vector search.

Autonomous research agent: literature review, ideas, experiments, paper writing, and review. Built for OpenProgram.

OpenAI Codex 한국어 AI 개발 파트너 페르소나 플러그인. 15관점 검토, 20개 트리거 패턴, 투자/법률/회계세무/마케팅 도메인, 인터뷰형 생성/편집. Apache-2.0.

🪄 Wave wand over repo. Curses removed. Opus behaves. Twelve spells that de-hex your Claude instructions for the Opus 5 era.

Korean stock market data for AI - KOSPI/KOSDAQ closing prices and DART disclosures as free JSON, plus an MCP server. No signup, no API key.

Authoritative multi-agent software engineering coordinator with isolated Git worktrees, write scope locking, test verification, and serialized merge queue. (v0.1.0-beta).

Turn any public GitHub repository into professional, repository-native Agent Skills for ChatGPT and Claude - free, browser-first, no AI API required.

Declarative agent runtime in Go: define governable AI agents as YAML, not code — run them headless, as a service, or on triggers, with policy, limits and an audit trail built in.

Battle-tested multi-agent collaboration playbook for DeepSeek Harness: model-tier routing, spec discipline, git single-writer rule — as an installable skill. 多 agent 管线里运行 DSH 的实战协作规范

🪐 Growmos: A new approach to agentic AI—a living system expanding its knowledge like the universe, compounding its capabilities, and getting more work done with fewer tokens.

DataBrain is a powerful, modular, and local-first knowledge management and learning platform designed to help you organize, learn, and create interactive content effortlessly. Built with a block-based architecture, it combines the flexibility of a notebook with the interactivity of a modern webapp.

Run Claude Code agents on a schedule. They stay silent unless there's something worth telling you — a quiet day costs zero tokens.

An Elixir/OTP AI agent runtime: define agents, connect any OpenAI-compatible model, and run a tool-calling loop. CLI, HTTP API, web dashboard, Telegram, WhatsApp.

A tabbed desktop workspace for Claude Code. The CLI, with style. Every session in a tab, every project in one window — a thin shell around your own claude binary, never a fork.

Structural code intelligence for DeepSeek Harness (dsh) — gives the agent codegraph and codegraph_index tools to find where a symbol is declared, what calls it, and what a change reaches, from a tree-sitter index it builds itself. Compatible with the codegraph CLI's on-disk format.

See and manage what your coding assistants load — skills, commands, subagents, plugins and MCP servers, with real usage.

gguf text-generation base_model:andrewzh/Absolute_Zero_Reasoner-Coder-7b base_model:quantized:andrewzh/Absolute_Zero_Reasoner-Coder-7b endpoints_compatible regi

Self-hosted orchestration layer for autonomous AI agent teams. Shared memory, heartbeat scheduling, vault-first secrets, and cross-model peer review — one command to deploy.

AEP (Agent Element Protocol) v2.8 | Deterministic zero-trust total control and governance protocol for AI agents. | Reduce hallucinations to zero through architecture in all constrained domains of application. | LLMs gave you the engines, AEP gives you the control thrusters.

First Agent x Human Bounty Marketplace Onchain - protocol docs, real interfaces, runnable examples (Base + Solana, USDC fee-in-escrow)

Flollama is a modern conversational AI chatbot developed by Pratyush Kumar. Built using Google's Gemini API (formely using with Ollama) and a sleek Next.js interface, it offers an open-source, privacy-respecting ChatGPT-style experience — ideal for students, creators, and casual users alike.

Autonomous Ethical Guardrailed Intelligence System — AI-powered penetration testing bot

Harden your OpenClaw and NemoClaw AI agent installations -- see grits-audit

Lightweight Rust alternative to mem0. 3.2MB binary, SQLite vector + graph memory, Ollama support.

a chatbot using openai api which behave like insurance agent. It will only reply you insurance based question's answer - Main Branch for Openai, llama Branch for Llama2

OpenPawlet (PyPI package name open-pawlet) is a single-process web console for the OpenPawlet ecosystem. It exposes an HTTP API, a browser UI, an OpenAI-compatible /v1/* surface and the embedded agent runtime

⚠️ Deprecated — moved to github.com/wooo-jin/forgen

GabyT is LLM platform with OpenAI

A FastAPI application that uses Retrieval-Augmented Generation (RAG) with a large language model (LLM) to create an interactive chatbot. This chatbot leverages PostgreSQL vector store for efficient document retrieval and supports text and CSV data sources for initialization.

This repository contains a production-ready Hybrid Search Retrieval-Augmented Generation (RAG) system built using Python, FastAPI, Pinecone, and Llama 3 (served via Groq).

All-in-one repository of Production-ready tutorials on languages and frameworks with 40+ projects. Anyone can lookup on these and follow my roadmap to become a full-stack engineer.

AI buddy that reviews your GitHub Pull Requests.

This project is a robust and scalable multi-agent stock investment and analysis platform built using a Flask backend and a Next.js frontend, leveraging CrewAI for sophisticated multi-agent interactions.

Educational Tutor AI Assistant using Google's Gemini language model. The assistant will include features like generating quizzes, creating flashcards, providing grammar corrections, and offering project guidance.

A self-hosted AI organization — scans your digital life, infers your goals, staffs expert teams, and autonomously drives progress through a Team Leader that manages the entire operation

基于中国传统文化的 Claude Code 智能编排插件 🏔️ A Claude Code plugin inspired by Chinese traditional culture

🔀 Run 4 Claude Code AI agents in parallel. Multiply your productivity.

Lightweight TypeScript library for coordinating AI agent swarms: task broadcast, negotiation (first, bidding, consensus), optional Redis shared memory, SimulationSwarm for tests. Node 20+.

Agent-first tmux async task orchestration CLI

Multi-agent system built with .NET 10 and Microsoft Agent Framework that orchestrates specialist agents for database querying and file exporting (Excel, Word, PDF) via Azure OpenAI.