Code agents

telegram userbot uses DanyAPI for chating

Personal AI that runs entirely on your Mac tool-calling agent, OpenAI-compatible inference server with tiered RAM+SSD prefix caching, push-to-talk dictation, and TTS. 100% offline on Apple Silicon via MLX. No cloud, no accounts, no telemetry.

gguf text-generation base_model:Qwen/Qwen3-Coder-30B-A3B-Instruct base_model:quantized:Qwen/Qwen3-Coder-30B-A3B-Instruct endpoints_compatible region:us

Proactive context synthesis for AI coding agents. Build the right context before the first token.

Manusclaw: Unleash self-reasoning CLI beasts to execute code, browse the web, and dominate tasks — across 12+ messaging channels, with voice wake, live canvas, SSH control, and multi-agent routing. No limits. Pure power.

Execution-time drift firewall for long-running DeepSeek Harness agents. Real-Harness tests: unsafe stale mutations 12/12 native -> 0/12; valid controls 7/7 both; post-SIGKILL unsafe continuation 2/2 -> 0/2.

Self-hosted audio API in one Docker container. Stem separation, mastering, MIR (BPM/key/chords), audio→MIDI, text-to-music + SFX (MusicGen/Stable Audio/Riffusion/AudioLDM2), diarization, speech enhancement, restoration, embeddings + zero-shot tagging, workflows, async + webhooks. REST + MCP. CPU + CUDA.

Privacy-first AI assistant for legal documents. Ask questions in natural language, get instant answers with exact sources. Scans contracts for risky clauses automatically. Runs 100% on your computer—no cloud required. Supports local AI (Ollama) or cloud APIs (ChatGPT, Claude, etc.). completely Free

Inter-agent security firewall for multi-agent AI systems: runtime prompt-injection filtering, Ed25519 trust attestation, and capability enforcement for LangChain, LangGraph, CrewAI, and AutoGen. pip install inter-agent-guard

🤖 Free open-source coding agent — like Claude Code, but powered by Hugging Face's free Inference API. No paid keys, just pure AI. Built with Python, Gradio, and LLMs.

Governance harness for decision-making systems with structured review, epistemic honesty, and retrospective calibration.

An AI engineering team you install into any Claude Code project — stack-agnostic agents plus a deterministic installer. Swap stack packs, not prompts.

Stateful local LLM inference manager with persistent KV-cache, native filesystem tools, and instant undo: built in C++ on llama.cpp

safetensors qwen3 speculative-decoding dspark dflash draft-model

Bo cham diem AI Agent dung Skill/Tool cho AutoCAD - Civil 3D - Revit BIM cau. 48 case, 6 hard gate, 197 test cho chinh bo cham.

CyberAgent — agent orchestration & human-agent collaboration: agentic project and task management where coding agents and people ship work together, with review gates, shared context and full audit. By Hyperspace.

GitSquad: A multi-agent orchestration framework for autonomous software development workflows on GitHub.

浏览器仪表盘：在 PTY 下拉起你本机真实的 claude / codex / opencode / reasonix / zulu 命令行，组成一个协作蜂群（共享收件箱 + 黑板 + 队长调度），并叠加多模型研究委员会与融合竞赛。Rust + React + Tauri。

A cross-harness, pure-skill implementation of the Fable 5 orchestrator pattern proposed by Anthropic — your agent as the boss; Codex, Cursor, and any headless coding agent as the crew.

Research-oriented cognitive AI architecture exploring memory, reasoning, planning, and adaptive learning using local LLMs.

Cursor Composer 2.5 powerpack for Pi: agent chains, dispatch teams, Pi-Pi experts, live subagents, Pi-to-Pi coms, damage-control safety, curated agents and mono-black theme. Install with pi install. Requires Pi ≥0.75.3.

Spec-driven agentic workflow for AI coding agents, with specialized subagents (research, plan, critique, execute, verify, debug) via markdown specs

Daimon: The Personal AI Conscience for the Agentic Era — an open-source framework for building a conscience layer for personal AI agents

Run Claude Code agents on your own VPS. A web manager spins up sandboxed Docker sessions with Remote Control, a built-in web terminal and GitHub OAuth, backed by Claude, DeepSeek or any Anthropic-compatible model.

中文 Agent Skill：陪普通用户用 Hermes Agent + Weixin iLink 五步搭建自己的微信 AI 助手，可选知识库、受控 Codex 编程与日常自动化。支持 Codex / Kimi Code / Claude Code / Hermes 安装，默认最小权限。

transformers gguf text-generation license:gemma endpoints_compatible region:us

Production-ready RAG for codebases using AST parsing, hybrid search, and LLMs with precise file & line citations.

🏆 Companion research environment to the ACM Vibe Science publication · EASE '26 / VibeX · DOI 10.1145/3816483.3816631 · Auditable, resumable AI-assisted research.

Multi-account Gmail MCP server — unified search/read/draft/labels across N Google accounts. Read + draft only by design (prompt-injection resistant).

Agent skills for building on Vobiz - voice API, SIP trunking, voice XML, and AI voice agents.

Agent skill + Python helper for the iKuai router private API — 14 domains, 105 verified func_names

Local-first AI workspace with persistent memory, real tools (files · shell · LSP · MCP · Office), and an opinionated agent team. Your data, your machine.

Open map data for your AI — free, no account, no API key. MCP server for Overture Maps: places, geocoding, routing.

Self-hosted, MCP-native web-search backend for AI agents: SearXNG meta-search + RAG with citations + GitHub project selection + Tavily-compatible API. Free & local.

One-command interactive switcher for Claude Code between Ollama Cloud (Free + Pro/Max), Claude, GLM Coding Plan (z.ai), Kimi Code (Moonshot), MiniMax, Xiaomi MiMo, DeepSeek API, and Amazon Bedrock. Auto-detects dependencies, prompts for API keys, launches Claude Code with the selected provider.

Your coding agent is smart. Your legacy codebase is the problem. Reify gives it the context to understand and safely change large, unfamiliar codebases — 100% locally.

docsforge — Crawler and Adaptive Harvest for Technical Documents like Code Language , API , Technologies. Search -> Identify URL -> Crawl -> Harvest Documentation

AI-powered IDA Pro REST API with 90+ endpoints. Autonomous RE agent, swarm worker, full SDK coverage.

transformers gguf code codeqwen chat qwen

gguf text-generation base_model:deepseek-ai/DeepSeek-Coder-V2-Instruct-0724 base_model:quantized:deepseek-ai/DeepSeek-Coder-V2-Instruct-0724 license:other endpo

transformers safetensors qwen2 text-generation unsloth code

From engineering intent to accepted work: native decomposition, HMAC-sealed atomic task contracts, bounded TaskMesh execution, and verifiable acceptance across Codex, Claude Code, Grok Build, Kimi, and Cursor.

Living Dream DSH - DeepSeek Harness desktop config framework with 8+ MCP servers, free model access, mobile remote, one-click install

Open-source Python framework to build, orchestrate and deploy AI agents: multi-provider, tool calling, RAG memory and desktop distribution.

AI-powered resume generator: parse, polish, preview & export. Built with Streamlit + LangChain + Playwright — JD-aware optimization with offline fallback, 3 templates, PDF/Markdown export.

Multi-agent orchestration and LLM model routing for DeepSeek Harness (DSH): semantic AI agent profiles, exact model routes, declarative teams and strategies, and bounded subagent delegation - a TypeScript plugin that adds no second runtime.

Self-hosted multi-agent workflow orchestration for Feishu/Lark with authenticated dispatch, retries, file intake, and traceable runs.

OMATS: A reproducible benchmark measuring LLM performance in multi-agent environments. Based on the 5 Stages of Model Capability framework.

通用 Agent Skill + CLI，将网页版 AI 作为外部 Agent，用于调研、评审与方案讨论，帮助降低宿主上下文占用和 API Token 消耗；当前仅支持 ChatGPT 自动化。

An adversarial feedback swarm approach to AI-first engineering

dsh-delegate: model-aware subagent delegation for DeepSeek Harness — per-call models, depends_on dependency gating, per-child personas, a durable run roster, audit events, and conversation-flow tool cards. | 给 DeepSeek Harness 的子代理委派加上：按次选模型、依赖门控、角色人设、任务花名册。

🖥️ 本地优先的自主 AI Agent 工作台 —— 分层规划 + ReAct + 自我纠错 + RAG 知识库 + MCP 协议。Web 工作台 / CLI / 三平台桌面版，支持 OpenAI·Claude·DeepSeek·Kimi 等 10+ 模型，数据不出本机，MIT 开源。

天机(Tianji):多 CLI 编程助手编排框架——六角色机械流水线(总控/分配器/监控器/架构师/实施者/审核者),账本单一真源,机制化不靠自觉

Hands-on code and examples for Week 5 of the Ready Tensor Agentic AI Developer Certification Program – building agentic systems with LangGraph, custom tools, and multi-agent workflows.

Forge – The AI Execution Layer

Visual MCP gateway composer for Model Context Protocol (MCP): discover and combine MCP servers and tools, manage permissions, validate integrations, and export secure configs for AI agents and LLM clients.

Source-linked AGENTS.md, CLAUDE.md, GEMINI.md, and SKILL.md examples from frontier labs and leading AI builders.

TAC is not a language for writing code. It is a language for thinking like an agent. (The TacFlow Agentic Code) is a domain-specific language (DSL) designed for autonomous AI agents within the TacFlow swarm ecosystem. It is not intended for general-purpose programming.

The first reference monitor for autonomous AI penetration testing agents. Mandatory enforcement, not prompt-based guardrails. Patent pending.

AI agent that recovers failed payments: root-cause diagnosis (rules-first + LLM tail), EV-ranked interventions, deterministic guardrails, payment-link execution — every action on a hash-chained ledger. Pre-registered eval: +10.24pp recovery vs tuned-naive baseline.

🧙‍♂️ Local-first autonomous data analysis agent. Private, self-correcting, and evidence-backed analytics powered by DuckDB, Polars & local LLMs.

Ditch Community Edition is a local macOS workspace for running, following, and returning to Codex sessions across multiple projects

Run local LLMs fully offline - chat, coding agent, image & music generation, knowledge/RAG, voice. Privacy-first, one CLI, no cloud required.

An unofficial native macOS (SwiftUI) client for dsh, the DeepSeek agent harness — sessions, live trajectory, tool approvals, models, goals, subagents.

ctx — a queryable code graph for coding agents, across Rust, Python, TypeScript and Go. Call graphs, blast radius, breaking-change gates, port parity. One binary, no LSP, no index.

In-game coding agent that autonomously plans, builds and self-inspects Minecraft structures (custom MCP bridge, deterministic generators, machine validators)

Yuj is a coding-agent harness that watches the LLM and keeps it on course. It maintains relevant context without extra LLM calls.

RizqAI — A Multi-Agent AI System for Financial Market Research, Risk Analysis, and Persistent Conversational Memory.

Curated Agentic AI resources: AI agent frameworks, tutorials, courses, projects, MCP tools, research papers, evaluation, security, and production guides.

Professional writing skills for AI coding agents: anti-slop editing and technical content writing. Claude Code + Codex plugin, installable via skills.sh. Install: npx skills add Kaos599/professional-skills

Official repo for of the ACL 2026 paper "Peering Behind the Shield: Guardrail Identification in Large Language Models"

Local-first RAG over your own document library (PDFs, papers, books, notes). Grounded answers with inline citations, eval harnesses that measures retrieval quality, epistemics and per-answer provenance.

A 7-layer architectural blueprint for building reliable, observable, and scalable agentic AI systems in production. Separates concerns like orchestration, context, security, and monitoring to ensure both agent behavior correctness and system performance.

跨产品 Agent 任务接力与委派。本机环境适配、额度切换、静默/可见 invoke。Claude / Grok / Kimi 等。

Open-source voice agent platform with visible reasoning. Build a roster of AI experts with their own retrieval, guardrails, rules and RAG sources - configured from the UI, with per-step model routing across cloud providers or fully local via Ollama.

Autonomous multi-agent due-diligence desk — LangGraph orchestration, agentic hybrid RAG, MCP tools, and a self-improving LLM-Ops loop.

Local-first AI project memory and control runtime for evidence, privacy, model routing, human approvals and cross-harness handoffs.

An AaaS platform and Agent Gateway with cross-platform clients. You can also use it as a client for Claude Code, Codex, and Pi.

Your AI coding crew in one Windows terminal - run Claude Code, Codex, opencode & Antigravity as a real team (lead + workers) in a native psmux cockpit. Event-sourced, no WSL, no API keys.

Lightweight terminal coding agent - drives a small local model or a frontier model with minimal context usage

peft safetensors gguf lora knowledge-distillation coding

Local AI Context Compressor with Claude Code, Codex and Cursor profiles, duplicate-context removal, Git diff prioritization, generated-file filters, conversation summaries, token estimates, reusable presets and clipboard/folder workflows.

Secure local REST, CLI, MCP, and agent bridge for IDA Pro 9.x

Token-efficient MCP file, shell, SSH and ops tools for coding agents — bounded reads, dedup, spill recovery and span edits.

Unofficial, third-party Python library and MCP server that provides a powerful and convenient interface to the RepeaterBook.com API.

Natural language testing for Model Context Protocol servers. Deterministic, open source, funded by LoopIQ.

A WordPress MCP server for AI agents that has to be trusted with a client's live site: 112 capability-checked operations, every write previewed, snapshotted, verified by reading the site back, and reversible. Elementor, ACF, Meta Box, Yoast and Rank Math included.

Kimi (Moonshot AI) official Formula API tools for DeepSeek Harness — web_search via kimi-official provider + 10 kimi_* tools, no DeepSeek/Exa/Perplexity key needed

AgentBypass — Omni Operator LLM Agent Skill (Cknb): Turn any LLM into RE / Pwn / CTF / Pentest / Protocol / Crypto / Mobile / Forensics operator. 20 modules, zero-dependency, all agents.

A Clojure-based Agentic AI framework featuring a Unified Concurrent Orchestrator. Executes parallel ReAct loops via local LLMs (llama.cpp) and a polyglot fleet of stateless HTTP microservices (C++, Python, Clojure).

Charterion: Multi-Agent Engineering Control Plane for ChatGPT Web Agents - orchestration, task dispatch, browser control, durable state, worktrees, evidence, review, recovery, and self-hosting.

🧠 Building an Agent collaboration system — skills that create, optimize, debug, and organize each other.

Ask questions about your PDFs, grounded in what's actually in them. FastAPI + Postgres/pgvector RAG API with background document ingestion, source-cited answers, and pluggable LLM/embedding providers.

Captain plugin for DeepSeek Harness: GPT planning, DeepSeek workers, independent review, adaptive multi-agent orchestration

Security-first multi-agent orchestration plugin for Claude Code — classifies every command by risk, gates state-changing operations behind consent, injects project context, and routes work to specialist agents. One unified plugin.

Multi-agent LangGraph orchestrator: a Telegram brief becomes a deployed project (code, CI/CD, domain, SSL) built by isolated Claude Code / Factory.ai workers.

Open-source VS Code extension — AI coding agent with local LLM support, multi-provider auto-discovery, and autonomous workflows

An AI agent for paid media — ad intelligence, creative testing, and ROAS optimization across PPC, paid social, and programmatic — backed by real ad-platform APIs.

Event-based long-term memory for LLM agents — associative surfacing over query RAG. Closed-loop episodic events, budgeted injection, tiered forgetting. Claude Code hooks + DeepSeek Harness plugin, one shared .memory/ format.