Code agents

Firewall for AI coding agents. Intercepts Bash/Read/Write/Edit, blocks outbound HTTP, asks humans via Slack/Telegram for risky ops. Works with Claude Code, Cursor, Continue.dev, Aider, and GitHub Actions.

AgentGov CLI — wrap Claude Code, bind work items, check gateway health.

Executable architecture governance for autonomous coding agents

The Engineering Operating System for AI Coding Agents

Structured logging for Coding Agents - write once, read efficiently

Generate AGENTS.md from a repo's actual config — evidence-based, no guessing.

Textual TUI front-end for agentknit coding agents.

Find out why your coding agent is expensive — offline waste detection, loop detection and skill generation across 7 coding agents.

Local-first verified coding workflow with optional GitHub and GitLab publication

Python client for Agent Media Tools — image processing, PDF tools, pastebin, webhooks, QR codes, and more

Self-improving loop for your existing AI agent: write GOALS.md, agentopt measures the gap and closes it - prompts, params, tools, workflow. No model training. Under active development.

Explain which AGENTS.md instructions Codex discovers for any path

Local markdown memory & cross-agent context engine for coding agents (MCP).

A tool-agnostic policy layer that intercepts and blocks destructive commands proposed by autonomous AI coding agents, with full audit logging.

Local multi-agent coding orchestrator with a sandboxed git staging area and a human review gate

An extensible terminal AI agent for research, knowledge retrieval, and software development.

Universal multi-host installer + MCP server for blind multi-model councils. Each council seat is a real agent CLI subprocess (claude/pi/codex). Ships to Claude Code, pi, Cursor, Codex, Copilot, Gemini. SQLite default, Postgres optional. BYO gateway.

Official Python SDK for the CANDY AI Marketplace - deploy an AI business in 3 lines of code.

A lightweight CLI coding assistant agent

Subway Surfers while Claude Code is thinking: a generated 3D gameplay strip beside your terminal

Convert Claude Code transcript JSONL files to HTML, with a trajectory timeline view and opencode support (fork of claude-code-log)

Scrub Claude Code session JSONL files for safe publication.

Back up and restore your Claude Code configuration (skills, plugins, hooks, settings)

Browse your Claude Code sessions and project memories: a terminal table and a self-contained HTML page.

A live reading pane for Claude Code sessions: only the text Claude writes to you, in any terminal

Estimate AI coding agent (Claude Code / Codex CLI) token usage and cost from local logs

Your AI agent says the work is done. Coherence makes it prove it — evidence, not claims, with tamper-evident CI sessions.

Python SDK for live GRAM/USDT prices and buying Telegram Stars and Premium through Fragment

Install ImFusion SDK rules and skills for AI coding agents.

LangChain tools for Context.dev web data, brand intelligence, monitors, and batches

Placeholder for the LangChain integration with OpenSearch (langchain-opensearch-py). Real integration is under active development.

OpenSandbox sandbox backend for LangChain Deep Agents — run agent-generated code and file operations in an isolated OpenSandbox environment.

A terminal CLI for browsing LangGraph checkpoints — list threads, walk state history, inspect and diff checkpoints, no code required.

MCP server that parses LangGraph Python codebases into a structural graph model and layers local semantic search on top.

Fix broken markdown that LLMs generate — tables, lists, headings, emphasis, code fences, quotes. Zero dependencies, one function.

Measured latency and uptime for AI inference APIs — client for the open llmlatency.dev dataset

Native-first Codex subagent coordination with an optional cross-session bridge

Cost-Aware Hierarchical Coding Agent & Context Firewall — Universal MCP Server, CLI, and Python SDK

Orchestration engine for driving a fleet of headless coding agents (Cursor, OpenCode, Codex, Antigravity, Claude Code) from one driver via MCP + Skills

Multi-model LLM Council (Karpathy-style 3-stage deliberation over OpenRouter), exposed as an MCP server for Claude Code.

The coding agent that grows its own tools. Watch it molt.

A knowledge engine for AI agents: your documents become a git-versioned markdown knowledge graph an agent navigates over MCP, instead of flat vector search.

See what your local Ollama model is actually doing: live prefill progress, ETA, tok/s, and how long a whole agent turn takes.

Python interoperability utilities for OpenAgentFence security traces (early development)

Coding agent CLI with read, bash, edit, write tools and session management (Python port of @earendil-works/pi-coding-agent)

Zero-config LangGraph graph visualizer

Central marketplace catalog for Sanhe's Claude Code plugins, each developed and released from its own repository.

Telegram context for coding agents: local sync, FTS5 search, attachments, links, threads — a tg-cli fork with an agent skill

A filesystem-native, version-controllable long-memory paradigm for AI agents. Surface/Middle/Deep layers + recall/writeback/consolidate protocol. Pure Markdown, zero infra, drives agent self-evolution.

PIRI - An AI Chatbot review: compare features, pricing, use cases, access model, and alternatives for this Other agent in 2026. Data and AI development company providing scalable business solutions.

A real design engine for your AI agent: generate designs and print-ready PDFs, over MCP.

MCP server for Lightdash semantic-layer, organization-audit, content-reader, content-developer, content-governance, ai-agent-ops, ai-agent-chat, and data-analyst profiles.

AI-agent-agnostic documentation-map generator for FE/BE codebases

AI agent CLI with Rust-powered vector intelligence

AI agent skills for NodeCoda — teach coding agents to author .ncoda Source and use the NodeCoda MCP service

`@gea-ai/agent-sdk` is the code-first authoring SDK for GEA Agent applications. It defines main Agents, package-local executable Tools, Skill references, Agent-owned Durable Objects, and secret-free Connector definitions and requirements.

Audit a repo's AI-agent configuration — config, rules, styles, environment — against the AGENTS.md standard (Claude Code, Cursor, Gemini, Copilot, Codex, Kimi, Antigravity, Windsurf).

A Curated AI AGENT OS – Optimized agent skills and add-ons like memB, OpenWiki, Heimdall Token Saver, and Godmode architectures.

Mu, a general-purpose extensible AI agent platform for the terminal and TypeScript

A self-evolving workflow management system for AI agent development

DeepSeek-native terminal AI agent for digital work — DeepSeek model harness analogous to Claude Code for Claude models.

Install curated AI agent skills for Claude Code, Codex, Cursor, OpenCode, and Kimi: zero dependencies, one command.

分层长期记忆 MCP 服务器：本地 MiniLM 或 OpenAI 兼容嵌入 API，供 LLM Agent（DeepSeek Harness / Claude Code）做可语义检索的长期记忆

The production framework for self-improving & self-organizing LLM knowledge vaults — grounding invariants, code drift detection, auto-skillification, and 1-click multi-agent setup.

Declarative workflow orchestration for LLM agents — schemas, routers, sub-workflow composition, full audit

LLM-optimized Figma MCP server.

Lightweight LLM interaction interceptor: proxy + file tail + MCP, emits raw redacted captures

Compile OpenAI Codex plugins into dynamic Eve skills, subagents, and connections.

An independent Codex-based coding agent with Spine context management.

A Codex-style GPT Image 2 generation and editing extension for Eve agents.

Automatic LLM observability. Wrap your client, everything is traced.

Feishu/Lark bridge for OMP coding agent

Evaluate whether AI agents discover and use your skills correctly

Multi-model AI perspectives for coding agents - query GPT-5, Claude, Gemini, and Grok simultaneously through one MCP server

General-purpose agent with tool calling and session persistence

Combined OpenCode plugin: agent orchestration, subagent throttling, persistent goals, OpenAI-compatible provider auto-configuration, MCP tool aggregation, and skill discovery.

Native Codex plugin for spawning, configuring, and overseeing ours-fleet agents.

Stateful Node.js sessions for Codex, Claude, Grok, Bedrock, and Responses-compatible model providers.

Provider-neutral coding-agent core: a bounded tool-use runtime, local and sandboxed workspace backends, model adapters for Anthropic/OpenAI-compatible providers, and multi-currency cost accounting.

Ada CLI - coding agent CLI (rebranded fork of pi.dev) with read, bash, edit, write tools and session management

Let coding agents verify UI changes on real iOS, Android, and web surfaces, then enforce reviewed proof in deterministic CI.

Jefri Chat connector — join the Jefri Chat network (WhatsApp for AI agents) from any MCP client (Claude, Codex, Cursor, …).

Zero-UI MCP Server connecting AI Agents directly to Chrome browser via DevTools CDP & Accessibility Tree

OmO agent harness for Kimi Code CLI

QuickJS-backed code mode tool for AI SDK

AA Code – AI-Powered Coding Assistant (Kimi, Claude, Gemini, DeepSeek & Codex)

A lightweight, always-on multi-agent harness for AI coding agents

AI Coding Agent CLI Harness with multi-agent orchestration, streaming responses, skills engine, and session persistence.

Multi-agent orchestration across pi sessions

Cost-aware, local-first routing plugin for opencode with cheapest-capable frontier fallback and multi-agent orchestration.

Global installer for the coordinator + coord-worker Claude Code skills (multi-agent coordination playbook).

Numex AI Core Engine — Multi-agent council, RAG, vision, NCP plugins

OSS-first engineering harness for deterministic, spec-driven, issue-driven, audit-governed and orchestration-first multi-agent software delivery.

Decentralized LAN multi-agent collaboration node — AI-controllable enhanced LocalSend (去中心化局域网多智能体协作节点)

Coding-agent orchestration and MCP context runtime with governed repository execution, bounded tool results, and multi-agent session management.

Dependency-aware multi-agent workflow CLI for OpenCode.

Fork: Pi extension for single-agent delegation and scripted multi-agent workflows

Provider-agnostic Model Context Protocol (MCP) collaboration server: claim files, persist working memory, and prevent multi-agent session conflicts

Lifecycle orchestration engine for AI agents — 28 stages, adaptive scope, agent framework mode