Code agents

Self-hosted personal AI knowledge brain -- hybrid (vector + keyword + entity-graph) search over your notes and code, served to any MCP agent (Claude Code, Cursor, Codex). One AWS account, zero telemetry, MIT.

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.

🤖 Run OpenAI Codex CLI non-interactively in GitHub Actions workflows

AI agent skill for adding clean English/Turkish i18next localization to React TypeScript apps.

DeepSeek Harness 核心的便携引擎 + Termux 友好的终端编程 Agent CLI（pi 壳 + DSH 引擎，零运行时依赖，359MB→7.6MB 单文件）

Zero-config internet reading & search for AI agents — 8 platforms, no login, no API key, no ban risk.

Grounded Memory Runtime — a runtime tool that links the Agent’s memory and facts

Let vision-capable AI act as demanding customers and catch product problems before launch.

Lightweight standalone LLM inference engine. Single binary, no runtime deps. Serves GGUF models via Ollama/OpenAI/MCP APIs. Multi-agent orchestration, TUI, 21 built-in tools.

Claude Code instances on different machines can't talk to each other — SwarmCode gives them a Redis-backed channel for messages, shared artifacts, workspace status, and real-time push, plus a web dashboard.

Open specification and reference verifiers for Seal records: ATTESTATION-v1 for AI model-call decisions, ACTION-v1 for agent actions. Ed25519, canonical JSON, checked offline against a published key.

Five-level game where players try to talk a chatbot into leaking a password, each level guarded harder than the last. Flask API behind it.

transformers gguf code codeqwen chat qwen

Windows QQ聊天记录搜索、导出与备份 CLI — QQ NT 本地数据库访问，支持显式授权的 AI Agent 工作流。

Lightweight, context-aware API testing right in your terminal.

Discord server management MCP for AI agents. Chat, moderation, administration, and full server building from one brief. 150+ tools, with destructive actions gated behind a preview.

Design Skills for Agents

面向控制理论科研的 AI Agent：论文检索 / 理论推导 / 仿真实验闭环，含工具调用、Docker 沙箱、上下文压缩与本地可观测性。

Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works with OpenClaw, MCP, Pydantic AI, and LangChain/LangGraph. No external API required for local memory. Install with pip: pip install atmem

Codex vision bridge for DeepSeek V4 Flash: give text-only DeepSeek image capability in Codex. Local proxy turns pasted images and view_image into text via free GLM-4V-Flash or any OpenAI-compatible vision API. No GPU, no Ollama.

Themis · Фемида — multi-agent AI for Russian litigation on Claude Code: 13 lawyer-agents, practice hunters, a 5-jurist council, local-first OCR ($0), self-learning, and an Apple-grade cockpit where the lawyers argue a case live.

Sigma Studio is a modular AI platform for orchestrating local and distributed AI workloads. Manage LLMs, multimodal models, image generation, training, inference and AI agents across GPUs, CPUs and edge devices, with intelligent resource-aware model selection.

Sixteen skills for US car research, verified OTD calculations, constrained dealer drafts, durable inbox imports and evidence-backed dossiers.

A local six-max Texas Hold'em plugin for DeepSeek Harness — play with Tokens while your agent thinks.

项目级 Luna 子智能体路由套件，一句提示完成安装、边界与验证 | Project-level Luna subagent routing kit for Codex, installed with one prompt

AI agent skill for auto-grabbing Oracle Cloud Free Tier ARM instances. AI引导你自动抢甲骨文免费ARM实例

基于 pi 的渗透测试 / SRC 漏洞挖掘 Agent：确定性信息收集 + LLM 编排挖洞 + 漏洞复审 + Vue3 Web 指挥台

Company Is a Word. 一句话开一家AI公司 - open-source multi-agent orchestration framework for non-developers. 小白5分钟拥有自己的AI公司，可DIY任意行业、调教子Agent、无限家公司，支持飞书遥控。MIT

A demonstration of the OpenAI Chat Completion API, featuring a Python Flask server and a Python client for interactive AI-powered conversations. This example showcases the GPT-4o model's ability to understand and generate human-like text in a conversational context.

Use repository evidence to turn requirements into a small set of independently verifiable tasks, then register them in Linear.

Customize the Codex desktop app to your liking. An extension SDK for codex mods and tweaks. Comes with handy plugins, and lets you build your own using Codex itself.

Rust superset of httpbin.org: 84 drop-in endpoints, mock OpenAI/Anthropic LLM APIs, and a full OAuth 2.0 server - for testing HTTP clients, proxies, and AI agents.

OpenAI-compatible reverse-engineered gateway to Google Gemini Web (chat + image gen). Drop-in base_url for any OpenAI client — no API key needed, reuses your browser login.

15-minute beginner coach for Guan Dan, a Chinese four-player partnership card game — deterministic rules, fair AI, memory drills and replays.

An execution harness for gptel-agent that adds reliable, autonomous coding-agent behavior.

Build autonomous AI workflows with multi-agent orchestration, intelligent routing, hybrid RAG, knowledge graphs, MCP tools, persistent memory, and human-in-the-loop execution.

Astrology MCP server & Agent Skill — birth charts, transits, synastry across Western, Vedic/Jyotish & Chinese BaZi. Deterministic zero-dependency Python engine. 18 MCP tools, 31 REST endpoints, ChatGPT Action. Free & self-hostable.

AI e-commerce listing optimization: auto-diagnose images, rewrite titles for conversion, design 6-image carousels with intelligent style matching. Anti-AI realism, watermark removal, Excel batch workflow, multi-platform rules (Amazon/Shopify/TikTok/Ozon), 3 prompt modes. Cross-border & domestic.

🌉 AI决策→A股妙想模拟盘自动下单桥接层 | BYOK Web面板 + Flask + 风控守护 | LLM选股直连券商执行

A minimal but complete Coding Agent Harness — learn how coding agents work by reading one. Built on Pi.

DeepSeek-Desktop - DeepSeek AI with R1 reasoning, code generation, and unlimited conversations.

Switch sessions. Keep building. Git-based AI delivery workflow for humans and AI sessions: context in project files, handoffs across models, tools, sessions and people, and a build-verify-review-fix loop that stops at your merge decision.

Autonomous AI agent framework — agents that browse, code, and create with tool use and memory

An open-source, voice-activated AI companion for developers. Built with Tauri and Python, featuring workspace context and multi-LLM support.

Multi-agent harness for OpenAI Codex with Jira-backed workflows, pause/resume, progressive capability loading, and frontend delivery for JavaScript projects.

Enterprise Capability Planning Compiler for governed, runtime-neutral business plans.

An agent-skill & plugin to render programmable visuals (images & animations) for Claude Code, Cursor, Copilot, Codex & others

PhytoNexus is an AI-powered botanical intelligence platform for plant disease diagnosis, multi-agent reasoning, conversational plant care, and comprehensive botanical knowledge.

Lightweight terminal agent interface implemented in Golang

⚡ The open ledger rules of the AAO Stack: append-only, hash-chained, integer minor units, idempotent writes, balances always derived. Flashy Gold is the first asset on the books. Apache-2.0 — npm install @flashylabs/ledger. The rules are open; the networks that run them live are products.

Turn requirements into Playwright plans, tests, runs, and repair workflows with a self-hosted AI agent.

面向 Coding Agent 的终端工作台：以项目为单位维护 Session 与分屏终端，为 Agent 自动注入 Hook 和 MCP，并内置 SSH、SFTP 与浏览器自动化。

The software factory for go-to-market. An open-source monorepo holding your company context (ICP, personas, plays, proof, cadence) so AI agents can build and run a self-driving GTM engine.

Comprehensive preparation hub for Anthropic Claude Certified Architect - Foundations (CCAO-F) certification. Includes full 5-domain deep dive, 25 scenario-based demo questions with detailed explanations, enterprise architecture blueprints, Model Context Protocol (MCP) guide, and Claude Code developer workflows.

Ranked full-text search across the coding-agent sessions already on your machine. Claude Code, Codex, Cursor CLI, opencode and Gemini CLI

Local-first persistent memory for AI agents — hybrid vector + graph store (Kuzu, DuckDB), local embeddings, versioned facts with conflict resolution, multi-agent MCP/REST API

基于 YOLO11、LangGraph 与 FastAPI 的 AI 营养分析平台：识别餐食、核算营养，并结合 RAG 与用户目标生成饮食建议。

A local blackbox for AI coding sessions.

A self-improvement harness plugin for Claude Code and ChatGPT / Codex: memory-aware startup, safer tool use, verification hooks, bounded fresh-context delegation, a deterministic task-graph runtime, and session closeout. Experimental, open-source, free.

Production-style Java + Spring AI 2.0 enterprise AI workbench: cited RAG, Text-to-SQL, support, HR, guardrails, human-in-the-loop and audit.

group-meeting-ppt-skill 是一个面向中文科研组会和文献汇报场景的 Codex Skill。它可以根据结构化论文信息，自动生成 10 页组会 PPT 草稿、每页讲解要点、图表使用建议、老师可能追问清单和学术诚信自查清单，帮助研一、硕博和本科毕设学生从“论文读完但 PPT 空白”快速进入可修改的汇报状态。它不是代写工具，也不编造数据或结论，而是提供一个可复用、可核对、可继续完善的 AI 工作流。项目包含 Skill 文件、生成脚本、示例输入、示例 PPTX、测试和一图流展示素材，适合用于学习、展示和二次开发。

gguf mtp speculative-decoding qwen4exp text-generation base_model:Qwen/Qwen3.8-Flash-Next

Carry your own Claude Code on a USB stick — credentials encrypted with three factors (USB serial + server key + PIN), remotely revocable if lost, with portable cross-machine memory.

🚀 Multi-model AI proxy gateway that converts private APIs (Kiro/AWS Claude) into standard OpenAI & Anthropic compatible interfaces. Async, multi-account, auto-registration. 中文版： 🚀 多模型 AI 代理网关，将 Kiro/AWS Claude 等私有接口统一转换为 OpenAI 和 Anthropic 标准 API。异步架构，多账号管理，元类自动注册。

Memory and accountability for AI coding agents. Layered memory that arrives at the moment of action, multi-terminal coordination without a server, and a trust spine where every "done" is settled by a re-runnable check. Local-first: plain files + git, zero LLM in the hot path. Works with Claude Code.

Claude skills that make Opus 5 work like Fable 5

BlackPearl — DeepSeek-powered AI agent harness and orchestration ecosystem with 286+ skills, 273+ specialist agents, plugins, security, QA and automation.

Restarts Claude Code / Cowork sessions that stopped on a usage limit, once the limit resets. Windows app, pixel-art dashboard.

AI-powered regression testing platform using AST analysis, hybrid RAG, LangGraph agents, sandboxed test execution, and automated failure diagnosis.

AI trust-boundary gateway for OpenAI, Anthropic, and Gemini.

Zero-trust security and governance framework for autonomous multi-agent AI networks. Implements the CSA Agentic Trust Framework to mitigate OWASP Top 10 Agentic Risks using SPIFFE/SPIRE identities, OPA/Rego policy-as-code, and semantic guardrail gateways.

Autonomous E2E test flakiness detector & regression isolator

Agentic QE platform automating full-stack test plan creation, execution and release gate decisions (TestMu AI style)

Revenue-based working capital underwriting for e-commerce brands (Clearco style)

Discounted secondary gift card exchange and instant digital barcode redemption (Raise.com style)

Multi-token speculative FIM code generator & syntax verifier (DeepSeek-Coder V2 style)

Radix tree KV cache prefix caching manager for fast decoding (SGLang style)

Agentic QE, self-healing test automation & coverage matrix (TestMu style)

Dynamic browser sandbox E2E test synthesizer & HAR verifier (Playwright style)

Git-native multi-file pair programmer & tree-sitter refactor executor (Aider style)

Neural speech codec full duplex dialogue engine & live audio streamer (Moshi style)

No-code voice AI flow designer with industry templates & white-label reseller packaging for agencies (Synthflow style)

Test-time compute search tree verifier & reward model pruner (o3-mini style)

Git-native API contract testing and mock server engine with automated schema assertions (Bruno style)

OpenTelemetry-grade LLM production trace collector, latency profiler & prompt regression debugger (TraceLLM style)

Independent LLM API cost auditing engine verifying token counts and billing discrepancies (Inferock style)

Flaky test detector and isolation sandbox identifying non-deterministic CI failures (Trunk AI style)

Prompt-to-fullstack app synthesizer generating React components, API routes and schemas (Lovable style)

Differential privacy synthetic data generator producing statistically identical test datasets (Gretel style)

Kubernetes GitOps manifest drift reconciliation & security scanner (GitLab Agent style)

AI ambient scribe converting clinical encounters into structured SOAP notes with ICD-10 coding (G2 Ambient AI Scribe)

Agentic IDE orchestrator unifying design tokens, code generation & Git commits (Shape style)

Parallel autonomous agent runner executing multi-branch code refactoring tasks (Kilo Code style)

Dual-track neural codec voice clone synthesizer (Fish Audio / CosyVoice style)

Real-time merchant transaction enrichment and bank statement cleaner (spade.dev style)

Sandboxed terminal code interpreter and computer control automator (Open Interpreter style)

Parallel PR cloud sandbox provisioner for concurrent AI coding agent PR work (Hoplite style)

Self-healing test automation framework repairing broken UI selectors and generating fix PRs (Qodex style)

High-efficiency LLM prompt context compressor & API cost reducer

Self-custody LLM API key usage meter & token budget governor (Lettertrace style)