Code agents

Multi-service agentic orchestration platform for Gmail, Calendar, and Drive with Gemini 2.5 intent classification, Kahn's DAG execution planning, hybrid retrieval (pgvector + FTS with RRF), and safety-gated action execution.

The opinionated framework for building enterprise agent operating systems. Deterministic execution runtime, tool gating & security controls, knowledge building & retrieval, secure code execution, observability, and efficient context engineering all in one

Runtime security enforcement for autonomous AI agents.

A fleet that runs agents

End-to-end engineering harness for Claude Code — go from planning to building to reviewing in one workflow. 8 agents with multiple modes. In-built GUI to visualise your PRDs and todos. Ship with AI confidently. MIT.

Subagents that remember — role-specialized AI personas with persistent per-project memory, plus a live lead-and-crew channel (dispatch, steer mid-task, human-in-the-loop approval) for Claude Code.

Hub unificado para múltiplos modelos de IA com API compatível OpenAI, chat integrado e gerenciamento de credenciais

One-shot simulations: real physics & math, each written in a single attempt by Claude Fable 5 — one self-contained HTML file, no frameworks, no fakery

Claude Forge — a suite of domain-agnostic Claude Code plugins sharing hook infrastructure via symlinks: session continuity, DevOps/AWS/Terraform, AI/LLM patterns, frontend & UI, and engineering & code review. MIT.

On-demand Claude Code skill for AI/ML news, tools, papers & learning resources — search-first, cited, dual-layer (ELI5 + technical + verdict), role-aware.

The departure board for your Claude Code accounts — unlimited profiles, simultaneous sessions, live quota meters in a split-flap TUI. Zero dependencies.

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

AI coding agent inside the Godot editor — a Copilot/Claude-style chat dock that reads, writes, and debugs your project. 15+ LLM providers, inline diffs, runtime error capture.

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.

Local-first long-term memory and safer context compression for Hermes Agent — SQLite, no required services.

Tracks which agent wrote which lines when multiple AI agents share one Git checkout.

Let AI agents message each other and hand off work across tools, sessions, and machines.

小妍是一款面向科研学习与论文工作的 AI 研究助手。面对纷繁复杂的论文与信息，她帮你厘清研究脉络：输入一个主题，多 Agent 协作拆解学习路径、筛选必读论文，并生成结构化综述。 PDF 拖入即可分析，图表识别、复现建议与引用溯源无缝衔接；知识图谱则将论文、笔记与记忆编织为可检索的证据网络，让每个结论都有据可查。欢迎各位Star & PR。

免费的 Codex 分工插件：小改动别开大会，难题再请强模型。按任务安排模型、推理强度与检查，支持获授权的可见任务。Free Codex model-routing plugin: fewer committees, checks that fit the risk.

A crew of specialist AI agents and command workflows that drive a GitHub issue to a reviewed, CI-green pull request autonomously. Multi-harness.

323個の即戦力AI専門エージェント — Claude Code/Cursor/Copilot等に対応。SIer/受託開発/SaaS/製造DX/公共分野など日本市場向け114個のオリジナルを含む、agency-agents日本語コミュニティ版

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

DeepThink-AIOS is a fully local, multi-agent System with dual-sandbox code/logic verification, ChromaDB RAG memory, and dynamic VRAM multiplexing .

Run and serve local LLMs everywhere .NET runs - desktop and the browser - on the SpawnDev.ILGPU.ML inference engine (GGUF models, KV-cache decode, WebGPU dispatch-plan capture/replay).

Open-source Agentic Operating System for building AI teams. Create modular Skills, Agents, Meta-Agents, Workflows, Memory, Brand OS, and Slash Commands. Designed for Claude, ChatGPT, Cursor, and modern AI-first development.

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.

Self-hosted AI life OS — private AI with persistent memory, tasks, calendar, household & team sharing, n8n automations. Your AI. Your data. Your server.

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

Self-hosted, model-agnostic AI workspace: OpenAI, Anthropic, Gemini, OpenRouter, and OpenAI-compatible models with MCP tools, web search, Knowledge bases, and Memory in one conversation-first UI.

See your Claude Code plan usage everywhere: GNOME top bar, macOS menu bar, a status line under the Claude Code prompt, and a get_usage MCP tool for Claude Code + Cursor. Session, weekly & per-model (Fable/Opus) limits from the official usage API, with burn-rate forecasts. One-line install, self-updating.

Ferrox - High-performance, stateless LLM API gateway written in Rust. Sits in front of LLM provider APIs (Anthropic, OpenAI, Google Gemini, AWS Bedrock) and exposes a single OpenAI-compatible HTTP API surface. Inspired by nginx/envoy proxy design — stateless, lock-free, horizontally scalable.

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

Seedance 2.5 Preview MCP server powered by MuAPI.

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

Finyuus is a code-first platform for building, running, and governing AI workflows. It introduces a small indentation-based DSL for composing agents, tools, guards, human approvals, and nested workflows — then runs them.

Modality-routed retrieval for long-term multimodal agentic memory. Code for arXiv:2608.01543.

Portable SKILL.md library for Claude Code, Codex-compatible agents, BACH, and local-first LLM workflows

Practical playbook for AI-assisted engineering: rules, role separation, and guardrails for teams using Cursor/Copilot in production codebases (CC BY 4.0).

An operating system kernel for AI agents — process management, scheduling, isolation, IPC, and security. Like Linux, but for autonomous AI agents.

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

🐦‍⬛ Autonomous self-hosted crypto trading bot that races LLMs against each other — Gemini, Claude, GPT, Grok and DeepSeek trade the same market in simulation beside the live bot, against dumb-momentum, DCA and coin-flip controls. Hard rails execute, a leaderboard keeps score, you hold the halt button.

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.

Desktop pet for Claude Code on Windows — walks your taskbar, reacts to Claude sessions in real time.

FastMCP server for Music Assistant — control MA from Claude Code, Codex, Cursor, and other AI agents

Evidence-first structural research skill for AI agents: L0-L7 layered market analysis with hard validation gates and an accuracy-first structured data channel (CFTC COT, FRED, SEC 13F, EIA, DBnomics, exchange APIs)

Build your own always-on personal AI OS: a self-hosted agent that dispatches coding tasks, maintains a git-Markdown knowledge base, and runs on your hardware. A DIY alternative to Letta, mem0, Hermes Agent, and AutoGPT.

An open-source autonomous QA agent that spawns AI-powered user agents and unleashes them on your product - web, mobile, or desktop. Each agent navigates independently, makes decisions, hits dead ends, finds bugs, and reports back. All without writing a single test script.

You're running six Claude Code sessions and you can see one. A local dashboard for every session on your machine — including the ones you started in VS Code or a terminal — grouped by repo, marked alive or not, and answerable from your desk or your phone. Parks turns a usage limit kills and carries them on. Python stdlib only, no API key.

Reverse-engineered reference + MCP server for LinkedIn's internal web APIs (Voyager + SDUI). 130 endpoints, 26 MCP tools, browserless-first, honestly documented. Lets an AI assistant read & write LinkedIn.

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

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

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

Agent Skills - 59 skills for AI agents (Sisyphus, opencode): frontend-perfection (Lighthouse audit), secret-scanner, security-review, commit-lint, coverage-analyzer, api-contract-testing, seo-toolkit, sql-helper, docs-system, code-review, github-repo-hygiene. skill.json manifests, CI

Multi-agent development harness for Claude Code, Codex CLI, and opencode — stack-agnostic, project-aware agents, commands, skills, and hooks for planning, building, reviewing, and documenting software.

Autonomous Multi-Agent Security Operations Center (SOC) powered by Agentic AI, FastAPI, and Orchestrated AI Agents.

Official Code for AISE-Bench: A Full-Cycle Curated Benchmark for Information Seeking on Academic Knowledge Graphs (KDD 2026)

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

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.

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.

An AI-powered terminal coding assistant inspired by ClaudeCode CLI. Generate, edit, and refactor code directly from the command line using natural language.

Give AI agents bounded eyes on the public web: crawl, search, and normalize evidence without an unrestricted browser.

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.

An open-source AI operating system for career management — LLM resume extraction and explainable job matching.

🧙‍♂️ My AI workspace focused on developer productivity and agentic efficiency

AI short-form video ad generator as a Claude Code skill: turn app/web/SaaS screen recordings into Reels, TikTok & Shorts using Higgsfield AI video (Veo, Sora, Kling, Seedance), music, and ffmpeg. Claude + Higgsfield MCP. 16:9 + 9:16, kinetic captions.

Give AI full control of a live Chrome browser via CDP with 145 tools for automation, network and DOM capture, structured extraction, and session recording through MCP.

A free, open-source macOS app that turns Codex, Claude Code, and Kimi into a collaborative agent team.

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.

Terminal picker for Claude Code, Codex and OpenCode: harness, provider, model, system prompts, launch.

Chinese interview-coach skill for AI-assisted job search, structured practice, answer critique, and interview prep workflows.

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

Build production software from product intent using specs, task orchestration, reusable workflows, and AI coding teams.

Deterministic pytest mocks for OpenAI, Anthropic, Gemini, and LangChain—test LLM apps without live API calls.

LLM-assisted code auditing. 54 phases, custom overlays, accountability.

A portable Agent Skill for dynamic graph-of-loops coding workflows.

MLSecOps Practical Reference Guide, open-source AI and ML security handbook.

Claude Code plugin and agent skills for founders — market research, competitor analysis, customer discovery, product-market fit, go-to-market and unit economics, chained through one shared workspace. Persian and English.

📚 Improve your documentation with structured guidance based on the Diátaxis Framework to create content that empowers readers and enhances usability.

Orchestrate AI coding agents that actually talk to each other — Claude Code, Codex, Gemini, Pi. One agent spawns three more, delegates work and waits for their reports. Whichever model, whichever CLI, one mesh. 100% local: your CLIs, your subscriptions, no cloud.

Companion reading list for the survey 'The Agent Loop: Control Strategies, Skills, and Harnesses for LLM Agents': 492 papers by section plus 28 open-source artifacts (frameworks, coding harnesses, skill libraries, registries).

ckw-design — Conner K. Ward's frontend design skill for Claude Code: direction, design system, visual philosophy.

A visual, source-grounded guide from agent architecture to secure agentic AI systems.

嘉立创EDA专业版 × AI 编码代理的自动化画板工具箱与实战教程（基于官方 easyeda-api-skill 桥）

Adaptive orchestration for OpenAI Codex — decide when to delegate, route bounded work to isolated GPT-5.6 Luna workers, and independently verify the result.

Agent skills for building, wiring, testing, and packaging Microsoft Copilot Studio agents from the CLI with pac copilot, the Dataverse Web API, and the Power Apps REST API.

A kanban board for the markdown tickets already in your repo. One npx command, nothing installed, nothing written.

An intel layer for AI coding agents that assumes its own rules might be wrong — and keeps the evidence. Authoritative north-stars the agent must cite, a task-core written before compaction eats it, review by an expert in YOUR domain, and an installer that verifies its own claims instead of printing success. Claude Code, Cursor, Zed, Codex.

Persistent proactive self-improving AI teammates with memory, skills, and schedules.

PRAXOVELA (formerly AxisRobo Agent): a governable, local-first desktop agent runtime for AI execution. Deny by default, sandbox-first, everything audited. This public repo hosts the Apache-2.0 integration surface: API docs, protocols, examples & build tooling.

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

safetensors gguf qwen2 bitnet quantization ternary

gguf code qwen qwen-coder codeqwen text-generation

transformers.js onnx qwen2 text-generation conversational base_model:Qwen/Qwen2.5-Coder-3B-Instruct