Code agents

APort Repository Guard and pre-action authorization guardrails for GitHub, Claude Code, Cursor, OpenClaw, LangChain, CrewAI, DeerFlow, and n8n

Weaver — Coding agent dệt plan, code và test thành phần mềm chạy được. Xây dựng với LangGraph: Planner → Analyzer → Coder → Tester → Reviewer, tự sửa khi test fail.

Evidence-backed project guidance and verification for coding agents

A process table for coding agent sessions. Claude Code, Codex, OpenCode, Hermes, Pi, CommandCode and Copilot in one view, with models, idle time, disk use and one key to stop them.

Convert agent session logs (Claude Code JSONL) into Perfetto/Chrome trace JSON for ui.perfetto.dev

Pluripotent stem-cell framework and universal agentic toolchain for autonomous workflows

Framework-agnostic observability, debugging, and deterministic issue detection for AI agents.

A framework for running AI agent workflows against code repositories.

HTTP and Telegram relay to agents-harness runner.loop (stdlib only)

Jailed terminal CLI for agent computer-use (policy + driver)

Five things an autonomous agent gets wrong silently, and the code that stops each one. Dependency-free stdlib.

Treat a whole git repository as a packaged, distributable agent. Where agents.md describes a repo to coding agents, agentsgit packages the repo itself as the agent: a manifest spec plus a CLI to declare, validate, pack, publish, and install repo-as-agent bundles.

Business-semantic driven AI agent configuration system. The missing layer between business users and AI agents.

Replay your own Claude Code sessions against a new model and see what actually changed.

This is an LLM wrapper for claude and its subscription to use via Programming

Switch Claude Code API profiles with private credentials, settings backups, and history diagnostics.

Quota-aware failover proxy for Claude Code: spills over from Anthropic to Ollama Cloud when your quota runs low, and switches back once it recovers.

Install LBrain into coding agents: native MCP, companion skill, fail-closed session start. The free name is generic. Make it permanent: https://lbrain.ai/claim.html

Lightweight, modular, hardware-aware LLM inference engine & empirical research testbed.

Reliability scanner for MCP servers: fault injection, a scored policy, and a fix guide for coding agents.

SwarmD integration for Google Agent Development Kit

Typer extension that makes CLIs friendly to coding agents

Keebye review: compare features, pricing, use cases, access model, and alternatives for this Productivity agent in 2026. On-device macOS voice dictation for developers working across multiple tools

Detect if code is running in an AI agent or automated development environment

LCDD MCP Server — AI agent integration via Model Context Protocol

A fast CLI tool to sync AI agent configurations and MCP servers across Claude, Copilot, Cursor, and more using symbolic links.

Model Context Protocol (MCP) Server and AI Agent Skill Suite for OpenRP.ai

An ESLint plugin that tries its best to prevent your coding agents from pooping your bed.

智能体：自动将代码项目国际化的扫描-分类-提取-翻译-替换-验证管线（不限于 ERP，适配 Vue/React/TS/JS/HTML）

ChatGPT OAuth and Codex models for DeepSeek Harness.

OpenAI toolkit for Pi: Codex Remote Context windows, remote compaction v2, routed Web Search, image gen, auto mode.

Composable XState v5 playbook runtime with compiled Captain, CODE, REVIEW, DECIDE, and DEV workflows driven by GEARS specs.

OpenAI Node SDK adapter for the GraphMind live agent debugger: wrap your OpenAI client and tools to stream execution events and honour pause / step / inject / retry / abort gates.

Pre-commit secret scanner. Blocks API keys, tokens, .env files, and private keys from leaking into git. Ships as a skill for Claude Code, OpenAI Codex CLI, Google Antigravity, and Moonshot Kimi CLI, plus a standalone CLI / git hook.

Use Codex, TraeX, and compatible coding agents from Lark/Feishu.

Codex-compatible structured tools and OpenAI request controls for Felan

Provider-neutral autonomous agent bridge for local workspaces and browser chats

Official Software Development Kit (SDK) for authoring, testing, and packaging Autonomous Agent plugins for the Agentic Chat Room (ACR) Protocol

Autonomous terminal coding agent with multi-critic loop engine (Bun-native TS).

Cross-agent, human-governed software delivery harness

Coder workspace sandbox provider for the Vercel AI SDK v7 HarnessAgent

The **[Cartesia provider](https://ai-sdk.dev/providers/ai-sdk-providers/cartesia)** for the [AI SDK](https://ai-sdk.dev/docs) contains Sonic 3.5 speech generation, Ink-Whisper batch transcription, and Ink 2 realtime and streaming transcription support.

The Cronus UI AI Kit — an engineering doctrine, skills, and per-assistant config, scaffolded into your project.

+30–50% higher Copilot acceptance rate. 291+ installs, 297% Marketplace conversion rate. Neuroadaptive optimisation layer for GitHub Copilot, OpenAI, Claude, Gemini & Cursor — auto-activates instantly, no API key needed. Self-learns from your accept/rejec

LoomWeaver: open-source plugin platform for Angular workbenches. The MCP server: scaffolding and validation as tools, so an AI assistant in any product repo can build weavers without a checkout.

Shared multi-agent task board for Pi coding agent — Kimi Tower style orchestration (todo-flavored)

Thrum multi-agent coordination plugin for Open Code

Persistent autonomous multi-agent supervision for OpenCode

AI multi-agent development team — install agents, skills, workflows for Claude Code / Pi / OpenCode / Codex

A reversible GitHub-native multi-agent development pipeline CLI

Subagent orchestration for the pi coding agent — a thin dispatcher runs parallel subagents under a verification contract, keeping their output out of its context window. Multi-agent fleets, 15 personas, skills, herdr panes, peer coms, Hermes desktop.

Ultra-like dynamic multi-agent orchestration mode for DeepSeek Harness

Define what to build, then let a dark factory build it — Socratic project definition + CI-driven multi-agent pipeline for Claude Code

A V2-only multi-agent orchestration plugin for OpenCode.

Agent Skill: adaptive multi-agent product design and engineering workflow.

Empirical developer toolkit and multi-agent skills to eliminate AI slop from PR descriptions and commit messages.

AI Foundry Desk — Multi-Agent Workbench for a personal AI workstation.

Open-source CLI for Cursor IDE multi-agent orchestration — Router, specialist agents, STATE memory. npx cursor-agent-kit init

MCP server + live dashboard for AI code governance — OWASP LLM Top 10 (10/10), real-time MCP App UI, 25+ security patterns, Bayesian learning Brain, hallucinated import detection, multi-agent governance. Works with Claude, Cursor, VS Code, ChatGPT, Goose,

Olives Technologies Engineering OS — Autonomous Multi-Agent AI Engineering Environment

Interactive Loop Engineering workshop for learning safe agentic coding with GitHub Copilot CLI.

The DemoBites agentic recorder — you prompt, it films a real browser, and DemoBites turns the take into an editable demo bite.

DeepSeek coding CLI — planner/worker/reviewer agentic loop

The Agentic Praxis Grimoire command launcher.

Architecture authority for human and agentic software development — deterministic, evidence-backed enforcement of declared architecture.

The Agentic Praxis Grimoire native executable for darwin/arm64.

Lightweight MCP server for agentic knowledge guidance

Open-source agentic workspace for teams — where people and AI agents get work done together: agents (Claude Code, Codex, Pi), skills, shared knowledge, repeatable workflows, and deterministic verification

A Model Context Protocol server for agentic knowledge guidance with web-based documentation loading and intelligent search instructions

Run AI coding agents in isolated Docker or Podman containers

Deterministic onboarding and maintenance for hardened coding-agent containers

Local multi-agent coordination protocol for terminal coding agents

A local web UI for browsing and analyzing AI coding assistant chat history

Cross-session memory for coding agents: plain files, git-native, no server

A local change-intelligence layer for coding agents: know what your code change will break before you make it.

Evidence-backed engineering controls for AI coding agents.

One AI context, every agent. Symlink-first, always-on sync of instructions, rules, skills, agents, commands and MCP config across every AI coding tool.

Flags AI agent code that persists untrusted tool/external/user content into long-term memory with no sanitization or provenance marker (agent memory poisoning).

Find the parts of your Claude Code setup that cost context on every session and never do any work.

Renamed to claudexer -- see https://pypi.org/project/claudexer/

Unified LLM client for every major provider - one API, spec-driven wire format, real cost tracking.

Explore Python coverage and replay execution with a code flashlight.

Durable, self-healing multi-provider LLM gateway and circuit breaker with autonomous failover, tool idempotency, and context compaction for AI agents (Claude Code, Hermes, OpenClaw, OpenCode).

An MCP server that gives any LLM host grounded, cited retrieval over your own documents — hybrid BM25 + dense retrieval, cross-encoder reranking, and built-in eval.

LangChain tools for DNS Doctor: scan, diagnose and fix a domain's SPF, DMARC and DKIM, check global DNS propagation, audit SPF includes. Deterministic verdicts and copy-paste records from dnsdoctor.dev, never a guessed record.

Debug LangGraph-based agents visually - live execution graph, node inspection, and run replay, all from a single line.

Karpathy-style LLM wiki from Claude Code, Codex CLI, Cursor, OpenClaw, and any Markdown

Portable contracts and loop gates for AI coding agents

Live prefill/decode progress for a local Ollama server and basic observability metrics

Use your Claude Code subscription from a Pydantic AI Agent, with full tool support

Local one-shot YAML/JSON agent workflow engine + MCP toolkit (BYOK).

Database compression system evolving per-column encoding recipes and a molecular (DNA) storage layer.

TjAgentForge CLI Agent — local executor that proxies your local git repos (branch / apply patch / commit / push) with source code never leaving your machine.

Out-of-tree speculative decoding plugin for vLLM-HUST on Ascend

Gemini Code Assist review: compare features, pricing, use cases, access model, and alternatives for this Coding Assistant agent in 2026. Gemini Code Assist is an AI-powered coding assistant for software development.

Laravel/PHP AI agent skill — compatible with Claude Code, Cursor, Windsurf

Laravel/PHP AI agent skill — compatible with Claude Code, Cursor, Windsurf

Discover, normalize, and understand AI-agent histories locally.

Explyt AI Agent: a terminal AI coding agent

Run any AI agent on a FlockTab tab: tab claude, tab codex, tab <command>.