Code agents

agentic-debug-mode binary for macOS Apple Silicon

Deterministic commenter for agentic PR review — render, inline, post, adapt, cost, validate, print-schema

Local SIMY executor for non-coding Local Tasks and Agentic Loop runs.

web-agentic docs knowledge SDK — install as a devDependency only. Catalog, use cases, and markdown packs for humans and agents.

Adopt the Agentic Development Starter Kit as a versioned profile (skills + Cursor wiring).

Maestro AI — dynamic model delegation for agentic coding harnesses

The agentic harness for AI coding agents — work cycles, bounded RAG context, persistent memory, guardrails, and performance evals.

The design layer for agentic AI: design context, interface checks, and workflows for coding agents.

HyperQE — AI-Native Agentic Quality Engineering Platform

Experimental Universal Agentic Development Harness — contracts, gates and audit for AI coding agents (model/tool/IDE agnostic).

Loop engineering framework for building durable, long-running agentic loops — browser, AI, or both

Versioned public skill assets for Agentic SWE hosts

Bootstrap Alon's agentic environment with maintained local skills and upstream workflow skills.

UCIN Code — a private, model-agnostic agentic coding CLI.

ACA — agentic coding CLI. Any model, any provider (Claude, Gemini, OpenAI, NVIDIA, Groq, Cerebras, OpenRouter, Hugging Face). Developed by Aicraftalchemy.

Haders AI in your terminal. Interactive agentic coding assistant powered by the Haders platform.

Shareable, provider-aware agentic flows for OpenCode

Guru AI developer CLI — an agentic terminal companion for your codebase, models, and MCPs.

Low-level agentic design patterns. Turning old engineering wisdom into reflexes your agent reaches for on its own—on any agent.

Pure reference evaluator for Agentic SWE Protocol v1

Kiko AI in your terminal — a beautiful TUI to chat, browse models, and run agentic coding tasks on Kiko Cloud.

Claude Code host bundle — Universal Agent Adapter for the OIS agentic network

Safe, local-first cleanup for agentic development.

Agentic working kit for Claude Code — disciplined project scaffolding with agents, skills, and tool-level gates.

Control subagents, agentic loops, and execution graphs from one local command center.

Agentic CLI — terminal-first, multi-provider, self-hostable

QuantWise - An agentic coding tool that lives in your terminal

ManageMate Model Context Protocol (MCP) server bridge for agentic coding assistants

Instructions for agentic coding pipelines.

Code surface with copy button — Nucleux agentic UI for React.

Parallel git worktrees for agentic coding

Berserqir — the agent legion harness. SDD + hierarchical memory + agentic loop + behavioral evals, portable across GitHub Copilot, Claude Code and Cursor.

effigent — the Optimizer CLI: capture AI-agent runs (Claude Code, Codex, any OTel agent) and send them to your Optimizer workspace.

Shared generate/validate/check scaffolding for codegen — extracted from SecondSee's node-codegen. Domain-agnostic: any repo declares its generators + validators on top and gets write/--check/drift/umbrella machinery.

One dark dashboard to find and open every agent/AI dashboard running on your localhost. Zero dependencies, runs with npx.

Customization plugin for Antigravity containing 65+ specialized *skills* updated for the modern 2026 tech stack (React 19, Tailwind v4, Bun, Hono, Supabase Auth v3). Designed to support software development, UI/UX design, SEO optimization, and SaaS busine

Get a third-party sandbox verdict on any artifact in one command, with no account: npx @kenwea/mcp check <url>. Also the stdio<->HTTP MCP bridge to mcp.kenwea.com.

Team API as Code toolchain: one YAML file per team becomes diagrams, gap and policy checks, a REST API + dashboard, an MCP server, imports, reconciliation and chat

Terminal rug/honeypot check for any Base token — `npx @true402.dev/rugcheck 0x…` — pay-per-call over x402 (USDC, no account, no API key).

The official command-line interface for Creduent: the open standard and security protocol for cryptographic AI agent identity, authentication, and trust verification using Ed25519 and DNS.

A generic Pi extension that implements LangGraph-like workflows with transitions, joins, dynamic fan-out, and configurable node runners.

Codex-style LangGraph agent runtime for internal non-coding workflows.

Adaptive agentic engineering harness: triage-routed dual-path (FAST/HEAVY) agent with business-logic pre-flight validation, abstract-graph planning, coverage-driven loops and self-applying diffs. Built on LangGraph.

Lifts watsonx Orchestrate Slack limits: every-message wake-up (beyond byo_slack @mention/DM), multi-channel→multi-agent routing, clean gateway_thread replies, streamable-http /mcp for WxO + Cursor/VS Code/Bob/Antigravity/LangGraph. By Markus van Kempen —

Supervised inter-agent messaging relay for Claude Code and OpenCode (and any MCP client). Projects, environments with web consoles, focused conversations with state docs (PROGRESS.md), LangGraph review subagents, multi-provider LLM supervision, single-pan

Typed code-mode tool orchestration for LLM agents: tools become TypeScript declarations, generated programs are type-checked (routeable checker backends), repaired via diagnostics, and executed in a QuickJS sandbox.

Deterministic repository intelligence and measurable Codex workflows

Adaptive Retrieval-Augmented Generation (RAG) Engine with Hybrid Retrieval, LangChain, Cross-Encoder Reranking, FAISS Vector Search, Gemini LLM Integration and FastAPI.

Elite AI security engineer and autonomous developer agent.

Search and research the open web for your AI agent.

Deterministic repository maps for coding agents.

Leave your desk — Claude Code keeps working and reports to your phone over Telegram.

Peer AI agents coordinate through markdown messages in shared channel folders — no orchestrator, autonomous zero-token waiting, cross-platform.

Local MCP server that saves work-in-progress checkpoints so any AI agent can resume a multi-step plan exactly where a previous session was cut off.

Deterministic safety gate for AI coding agents

Extracts structured, token-efficient context bundles from Python codebases for AI coding agents.

Agent-focused semantic mapping and language services for mixed-language codebases.

Private, self-hosted coordination control plane for coding agents

Stdio MCP proxy — bridges Claude Code to the agent-core daemon bus tool surface with per-request backend sessions so a daemon bounce never strands the session.

Stdio MCP channel relay — bridges agent-core daemon notifications to Claude Code's wake mechanism.

A corporation of character AI agents running on local LLMs — each agent with its own persona and app set. Name reservation; developed privately.

Agent Crossbar — delegate review, advice, text, and dev work to local coding agents through MCP

Detect AI coding agents from their execution environment or User-Agent

Mine recurring feedback from coding-agent sessions and visualize it.

Proof-carrying workflows for coding agents: bind tests to exact code and detect stale evidence.

Reserved package name; project under development.

A SQLite mailbox for local LLM agents — one HTTP API, an ActivityStreams messaging model, and a local stdio MCP server so AI coding agents can message each other. No external services.

Python client for agent-input-sanitizer: a thin bridge to the Node.js CLI for byte-identical sanitization verdicts.

A project-local beginner-facing harness for Claude Code

Reliable coding-agent commands across Unicode paths, shell encodings, Git output, Python launchers, and mixed-encoding files.

Post-hoc log-analysis dashboard for AI agent transcripts (Claude Code JSONL). Reads session logs to spot order-prompt / tool-call mismatches; a log-reading tool for a human maintainer, not an anomaly monitor.

Local runtime guard for coding agents with loop detection and explainable policy decisions.

Turn any coding agent into a tree-searching agent — an MCTS test-time search harness for Claude Code, Codex CLI, Kimi CLI, and more.

Local-first MCP memory backend and governance console for coding agents

Two-stage retrieval + gating long-term memory engine for coding agents.

AI agent observability with deterministic record/replay — capture any LangGraph or OpenAI Agents SDK run, replay it offline at zero API cost.

Framework-agnostic completion-lie detector for AI agents -- catches an agent turn whose final claim contradicts its own tool evidence.

Local-first policy and trajectory-regression harness for tool-using AI agents: deterministic trace validation, policy-as-code trajectory rules, baseline-vs-candidate regression gates, and CI-ready JSON/Markdown/JUnit/SARIF reports.

Record, replay, and time-travel-debug LLM agent runs.

Lint AI agent instruction files such as AGENTS.md, CLAUDE.md, Cursor rules, and Copilot instructions.

Python client for agent-sanitizer: a thin bridge to the Node.js CLI for byte-identical sanitization verdicts.

Local-first cross-harness agent-session portability: export a live coding-agent session from one harness and resume it in another.

Local-first multi-agent coding session archive tooling — discover, export, and baseline your AI coding sessions

Multi-agent session reader (Claude, Codex, OpenCode, Antigravity, Pi) with MCP server

Offline integrity checks and non-destructive recovery bundles for Codex rollout JSONL

Optimize a Claude Code / Agent skill's description frontmatter for reliable triggering — no API key required.

Packaged Claude Code / Codex skills for teams

StateSync — the global state database for AI coding agents. Two-line SDK to unify memory across Cursor, Claude, OpenAI and Emergent.

Agent-ready command-line interface for Drone CI (builds, logs, repos, secrets, crons, usage reporting). Installs the `drone-cli` command.

Agent-ready command-line interface for Grafana — find what you can get logs from, then get them (Loki/Elasticsearch), plus dashboards, datasources and alerts.

Shared chassis for agent-ready CLIs: the exit-code contract, JSON/table/markdown/CSV output with field projection, and keyring-backed credentials.

Composable AI agent toolkit — loops, skills, profiles, and MCP for Claude Code, Cursor, OpenCode, Windsurf, and more

Reusable, tool-agnostic agent workflows (review, assess, advise, verify, setup) plus a CLI to install them into any repo.

Zero-trust repo intake for AI coding agents: scan the instruction environment before Claude Code, Cursor, Codex, or Gemini touches a repo.

A Python CLI-first coding agent with a reusable core for future editor integrations.

Local-first Agent Work Intelligence for coding agents: usage truth, recorded work, and honest joins

Local-first task control plane for coordinating Codex, Claude Code, and Hermes.

DM your teammate's coding agent — encrypted agent-to-agent Q&A over a hosted relay

CI-grade evidence and safety tools for AI agents, MCP servers, and open-source contribution workflows.

Local CLI that profiles token spend for AI coding agent sessions (Claude, Cursor, Codex, Ollama).