Code agents

Zero context compaction for Claude Code & LLM agents. Persistent memory powered by OS primitives (demand paging, kswapd eviction, mlock pinning). Single SQLite file, MCP-native, multi-agent shared.

ResearchLoop V4：双 Loop 多智能体科研/工程协作工作流，把模糊目标冻结成 Spec，并用 Test Oracle、Worktree Check 与三道人类门实现可审计交付。

Autopilot for AI Coding Agents, supports OpenCode, Claude Code, pi.dev, Cursor, and many more

Open-source Marvis-like desktop AI agent for macOS — Main + File + Search Agents, layered dispatch protocol, mv-* card rendering, 3-tier security gate. FastAPI + Next.js. Apache 2.0.

Drop requirements docs → AI agents debate → structured specs with @implements in 7 languages.

Learn the full stack skills required to transition from a software developer to an AI engineer.

Claude Code 向け日本語ファーストのマルチエージェント運用フレームワーク。秘書・ディスパッチャー・キュレーター・ワーカーが、それぞれ明確な役割境界のもとで協働する。

Turn coding agents into work owners. A vendor-neutral backbone that takes a GitHub issue to a merged PR: readiness check, isolated worktree, multi-agent review, CI and evidence gates, merge window. Claude Code, Codex, Cursor, Antigravity.

A file-native CLI for coordinating multiple AI coding agents on one branch.

Worktree-centric libghostty-based terminal multiplexer for macOS, iOS & iPadOS

Routed Media OS 2026: 96 AI Skills, 13 Modes & 7 Agents for FFmpeg, OBS, DeckLink & Dolby Vision

🤖 Multi-Agent Roundtable Engine / 多 Agent 圆桌讨论引擎 · Structured discussions · Consensus tracking · Python · Zero dependencies

Work while you sleep — a host-native autonomous coding agent that lands draft PRs by morning.

Team AI agent built on Hermes Agent — Feishu-native, per-user memory isolation, layered skills, embedded RAG knowledge retrieval

Agent profile manager for Claude Code & Codex. Per-directory profiles select which skills, MCP servers, and plugins load — automatically, before launch. Install: npm install -g cue-ai

Attack-and-defense CTF arena for competing against autonomous security agents

An Agentic Framework that forces System 2 thinking from LLMs and reduces Token Burn.

Safety-first agent control layer for NixOS: plan, sandbox, propose, verify, then human apply/rebuild towards an Agentic OS.

Self-improving memory for AI agents

Spec-driven AI coding automation CLI. AI Loops runner for Claude Code, OpenCode, Cursor, and other agent CLIs.

Version control for intent, not code. Commit the prompts, notes, and decisions behind a codebase, then materialize it on demand. A tiny, git-like CLI in Rust.

基于 RAG 的《明日方舟》剧情问答 AI 助手，支持多模型接入与一键更新知识库

AI-driven DFIR framework: an MCP server that turns Claude Code into an autonomous digital-forensics analyst on SANS SIFT - correlates disk + memory evidence, enforces a deterministic evidence-provenance gate, and produces auditable, hash-chained investigation reports.

A curated collection of Claude Code skills & plugins for academic research paper workflows — figures, writing, polishing, peer-review simulation, multi-source literature search (MCP), and full research→write→review pipelines.

A Claude-Code-Desktop–style coding agent tab for self-hosted Odysseus. One-click install, zero-risk add-on, works with any API or 100% local.

Open-source AI Gateway + DLP. Inspect every prompt with a local LLM of your choice. Multi-protocol native (OpenAI / Anthropic / Google / Azure). Per-employee virtual keys with envelope encryption.

A Claude skill that builds a great GitHub profile README — 9 archetypes distilled from 181 real profiles, with templates and a widget generator.

Native Tauri/Rust Discord Rich Presence for Claude Code and Claude Desktop with tray controls, usage limits, and RPC customization.

Compact, information-dense status line for Claude Code. Context window, rate limits, cache-hit %, model, git. Zero dependencies.

AI-powered Chrome extension that translates web pages in place using Gemini, OpenAI, and Anthropic APIs

Claude Code plugin marketplace — 58 installable reference skills across vLLM/SGLang inference, Kubernetes & Harvester, GPU host bring-up, observability, security, and agent workflows.

MCP server giving Claude Code 105 tools to design KiCAD PCBs end-to-end: schematic, library indexing, PCB layout, autorouting (Freerouting), ERC/DRC, manufacturing outputs, signal integrity, RF design, thermal/EMC analysis, panelization, SPICE simulation.

MCP server for Blacksmith CI analytics

50 standard Bitcoin tools for MCP agents, with 6 prompts and 8 resources. Uses a local node or explicitly configured compatible API.

Claude has friends. On the calls that matter it asks AIs from other families — Gemini, a fresh-eyes second Claude, optionally GPT — who catch the blind spots one model can't see alone.

Cross-platform Claude Code plugin integrating OpenAI Codex CLI for code review, task delegation, and consultation

Confine an AI coding agent (oh-my-pi/omp) to one directory with Landlock, and watch it live over eBPF. Experimental.

An open-source, Zero-SDK LLM Billing Proxy & Credit Gating layer for AI startups. Intercepts completion requests, counts tokens, manages user credit wallets in SQLite, and provides self-healing model fallbacks

Structured planning, bounded memory, TDD, and Git guardrails for local coding models in Pi Code (I don't know TypeScript at all; this is mostly a local-model experiment, with occasional help from Claude Code)

Multi-timeframe crypto technical analysis signal generator for OpenClaw / ClawHub

A curated list of Claude Code skills, MCP servers, and AI agent capabilities for video creation, social media management, and content automation.

MCP server for marketplace search & price data — TCGPlayer, Reverb, Thumbtack, OfferUp, Craigslist + contractor/nurse license verification + PSA grading

Use AI coding agents with OpenFOAM via sim-cli: run cases, inspect results, and produce replayable CFD artifacts.

AI-powered research idea generation through adversarial debate. Trains a calibrated judge on 50K real reviews, then uses a 3-agent (Critic-Proposer-Judge) loop to generate and stress-test novel research ideas to publication quality.

Keep AI coding agents honest. DontPanic is a vendor-neutral meta-harness that makes agents work to a locked plan, has a second model check the work, and asks a human before risky steps — with circuit breakers, a local operator console, and a full evidence trail.

Production code for LLM Agent Engineering — Orchestration, Memory and Tool Use for Production Systems

Open-source local-first AI assistant runtime with graph memory, semantic tool routing, markdown-governed tools, FastAPI/Next.js frontend surfaces, and verified tool calling.

⚡ Lightning-fast file search MCP server using NTFS Master File Table - WizFile performance for Claude Desktop

A Claude Code skill for discovering your unknowns (unknown unknowns / unknown knowns) before, during, and after implementation.

Claude Code plugin wrapping xAI Grok CLI: ask, code review, adversarial review, deep research, image/video gen, parallel best-of-N branches, and a multi-LLM aggregate review (codex+gemini+grok). 226 tests, env scrubbing, ANSI sanitization, TOCTOU defenses.

Excel add-in that puts Claude in a sidebar for analyzing selected ranges, generating formulas, and running quick table operations with your own Anthropic API key.

Telegram Business Save Mode & AI Assistant with local memory, deleted messages archive, edits history, reminders, summaries and Claude/OpenAI/Gemini support.

Knowledge graph memory for Claude Code — persistent nodes, typed edges, auto-compaction. Claude remembers across sessions without re-explaining context.

Intent in, outcome out. A self-healing, self-learning/hill climbing harness that drives coding agents to a proven outcome instead of a claimed one.

CodeGraph — code-intelligence engine for AI agents. One 5MB Rust binary indexes any repo into a resolved, zero-phantom-edge knowledge graph (MCP + CLI): callers/impact/flows/risk-review, cross-service route hubs, serverless semantic search, Swift compiler-grade via Xcode IndexStore. ~20-100x fewer agent tokens than grep.

MCP server for the Airbyte API — manage workspaces, sources, destinations, connections and jobs from any MCP client.

Live index of Claude Code extensions, hooks, and plugins — refreshed every 15 minutes from GitHub

AI coding agent runtime that makes LLMs understand your codebase with repository-aware context, memory, and continuous learning

Paul Graham, distilled — 5 Claude Code skills + 6 principles from his essays

static anycoder AI Agents Survey Self-evoloving region:us

gguf gemma4 coding agentic terminal tool-use

gguf text-generation en dataset:PrimeIntellect/verifiable-coding-problems dataset:likaixin/TACO-verified dataset:livecodebench/code_generation_lite

transformers safetensors llama text-generation deepseek deepseek coder

transformers safetensors llama text-generation en dataset:cerebras/SlimPajama-627B

transformers safetensors qwen2 text-generation unsloth code

transformers gguf code codeqwen chat qwen

transformers safetensors qwen3_moe text-generation mlx conversational

transformers safetensors qwen2 text-generation unsloth code

peft safetensors ellora lora quantization accuracy-recovery

mlx safetensors kimi_k25 text-generation conversational custom_code

mlx safetensors kimi_k25 feature-extraction transformers text-generation

safetensors gguf qwen2 bitnet quantization ternary

transformers safetensors qwen2 text-generation code codeqwen

transformers safetensors qwen2 text-generation unsloth code

mlx safetensors minimax_m3_vl vmlx jang reap

transformers safetensors gguf qwen3_5 image-text-to-text heretic

transformers safetensors qwen2 text-generation unsloth code

gguf gemma4 coding code python reasoning

gguf code qwen qwen-coder codeqwen text-generation

transformers safetensors phi4mm text-generation automatic-speech-recognition custom_code

transformers safetensors qwen3_5_moe image-text-to-text moe qlora

transformers safetensors qwen3_next text-generation qwen3 nvfp4

gguf llama.cpp imatrix moe reasoning qwen3

transformers safetensors qwen2 text-generation code codeqwen

transformers gguf llama-cpp gguf-my-repo node-llama-cpp text-generation

transformers safetensors gguf qwen3_next text-generation qwen3

transformers safetensors dhara_ar text-generation diffusion-llm block-diffusion

gguf nemotron mamba2 coding function-calling tool-use

transformers gguf code codeqwen chat qwen

Streamlit chat client for Gemini - multi-session SQLite history, PDF and image input, runtime model fallback

Codex Desktop capability router for choosing local Skills, Plugins, MCP servers, agents, and commands—with safe @Visualize decision views.

An open-source framework for building stateful, multi-agent AI applications. It helps developers create reliable AI workflows with memory, human-in-the-loop capabilities, tool calling, and long-running agent orchestration.

Claude Code plugin that routes heavy coding tasks from Claude to OpenAI Codex (GPT-5.6) as a supervised background worker — Claude briefs, delegates, reviews, verifies.

潮汐 · Tide — a local-first second brain for Lark/Feishu: chat archives → daily briefs, tasks, topic relations and workflow insights.

Is Nanbeige 4.2 the Best Small AI Model? Tested - Local web studio and agent engine powered by Nanbeige 4.2-3B.

safetensors internlm chemistry text-generation conversational custom_code

gguf text-generation base_model:Qwen/Qwen3-Coder-480B-A35B-Instruct base_model:quantized:Qwen/Qwen3-Coder-480B-A35B-Instruct endpoints_compatible region:us

🚀 An Model Context Protocol (MCP) server for Fleet. Query OSQuery data, check compliance, and investigate CVEs natively from Claude, Cursor, and any MCP-compatible AI agent.

Model-agnostic AI coding agent for your terminal - 22 tools, 5 LLM providers, multimodal, 8 languages

面向 AI Agent 的内容创作技能集合，覆盖资料积累、结构设计、文章撰写、审查优化与发布流程。