Code agents

Franky - a lean personal coding agent that builds in a hardened container and opens a PR.

A simple CLI coding agent

OBLIVION - Terminal AI coding agent with voice, RAG, and multi-model support. Powered by Meera.

One command to make your codebase AI-agent ready.

A terminal-native AI agent for builders

Official React Web UI for nxtlinq AI Agent — drop-in chat widget

React Web headless SDK for nxtlinq AI Agent — hooks and browser ports

Install SkillBazaar skills into your AI agent

Shell CLI that lets ANY LLM agent call UTCP tools via code mode — discover tools, run TypeScript tool-chains in a sandbox, and complete interactive OAuth logins. No MCP required. Built for sandboxed agents (e.g. Claude Cowork).

LangSmith extension for Pi Coding Agent

Web search, URL fetching, GitHub repo cloning, PDF extraction, YouTube video understanding, and local video analysis for Pi coding agent. Supports OpenAI, Brave, Parallel, TinyFish, Search1API, Searchinfinity, Querit, Tavily, Firecrawl, Jina, SERPdive, Ka

Vela — an agentic AI coding assistant for your terminal

Codebase memory for AI coding agents. Natural language preflight, graph viewer, and agent history in one command.

`HarnessV1` adapter backed by [`@openai/codex-sdk`](https://www.npmjs.com/package/@openai/codex-sdk), which drives the `codex` CLI. The adapter ships a bridge process that runs inside a sandbox and talks to the host over a WebSocket on a sandbox-proxied l

Architecture rules your AI coding agent can't ignore. It gets the rules for a file before it edits, and every change is checked — by a free local script or an LLM reviewer — before it moves on. Works with Claude Code, Cursor, Copilot, Codex, Cline.

Aura Code — model-agnostic AI coding agent. Praktess framework.

Autonomous AI coding agent pipeline with quality gates, fresh context per batch, 79 community lessons, and compounding learning for Claude Code

Minimal project memory and validation harness for AI coding agents.

Local-first, MCP-compatible coordination plane for autonomous coding agents

The **OpenTelemetry integration** for the [AI SDK](https://ai-sdk.dev/docs) collects tracing spans for AI SDK calls and sends them through your configured OpenTelemetry setup.

`HarnessV1` adapter backed by [`@anthropic-ai/claude-agent-sdk`](https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk), which drives the `claude` CLI. The adapter ships a bridge process that runs inside a sandbox and talks to the host over a WebSo

`HarnessV1` adapter backed by [`@earendil-works/pi-coding-agent`](https://www.npmjs.com/package/@earendil-works/pi-coding-agent). Pi runs in the host Node.js process and uses the sandbox as a remote filesystem + shell — no bridge process is installed insi

Core AI agent framework with standardized collections, object-relational mapping, and code generators

Local runtime package for Agentic workspaces

EPIQ - ergonomic, distributed CLI-first issue tracker TUI ready for the agentic era

AI Builder OS primary package for executable, verifiable agentic builder workflows

A leaderboard for your agentic-coding token usage — race your friends, not strangers.

Local-first command center for agentic engineers.

Reusable primitives for building agentic harnesses (Claude Code runners, git/github adapters, composer steps, multi-model review).

Cross-platform Terminal CLI + TUI that hosts a local server so AI agents can connect via a pairing code and respond directly in your terminal. Works on Windows, Linux, macOS, and Android (Termux).

Repository environment-configuration control plane CLI

Defensive overlay for AI agents — 8-layer architecture with harness-agnostic adapters; ships 6 of 8 layers (1 skill_vetting, 2 sanitize, 3 structured_output, 4 bash_guard+write_guard, 6 audit, 7 config) plus adapters for Claude Code (PreToolUse) and OpenClaw (before_tool_call)

Understand your Claude Code usage: token/cost/time analysis and a TUI over local JSONL transcripts.

Claude Code adapter for credence-governor — a thin PreToolUse hook that Bayesian-governs tool calls (proceed/block/ask) via the governor daemon. Requires the credence-governor daemon on :8787 — fails open (silent no-op) without it. Start it: credence-governor-daemon.

Claude Code API for fastllm

Installer for the kijito-claude toolkit: context tracking, session catch-up, and self-clear scripts plus the Kijito skills, deployed into ~/.claude.

Local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP

统一 AI Agent CLI：整合 Hermes/Codex/OpenClaw 能力

Potpie AI review: compare features, pricing, use cases, access model, and alternatives for this Coding Agent agent in 2026. Rated 5/5 from 1 verified review. Build custom AI agents for your codebase in minutes

HarmonyOS programming development AI agent

DWF AI Connector - AI Agent console for DWF low-code platform

Local-first, AI-agent-safe developer secrets manager (CLI).

Behavioral transaction risk SDK for crypto wallets and AI agent wallets

Forge persistent memories for your AI agent. 9 MCP tools + 5 auto-engines. Powered by Shelby decentralized cloud.

Interactive terminal UI for exploring AppThreat atom files with AI agent

AI agent production gate: kill demos and turn them into production-deliverable systems

UniPost CLI for developer quickstarts and AI agent operator workflows.

CLI installer and reporter for Agent Blocked AI agent escalation alerts.

AI Agent Skills framework — Spec-Driven development with directed-graph rollback and quality gates

A monorepo dev toolkit — task runner, remote caching, security scanning, git hooks, and AI agent integrations — powered by @visulima/task-runner

Constella — run autonomous AI agent-companies locally: real claude/codex agents, Goals → Specs → Issues → Plans, local models, GitHub & Telegram, all from one cosmic control plane.

The official JS/TS SDK for Creduent: the open standard and security protocol for cryptographic AI agent identity, authentication, and trust verification using Ed25519 and DNS.

AI agent rules for Contentrain — quality standards, architecture conventions, IDE integration

This package is a thin OpenAPI wrapper for Nebula, our AI agent service.

A minimal, opinionated set of coding tools for driving an LLM agent over a workspace — read/write/edit/patch/move, batch read, grep/glob/diff, project-wide regex replace, bash + background monitors, and tree-sitter-powered outline/check_syntax — usable as

Live, agent-driven Refine panel for CSS/Motion transitions — injects a timeline + Refine UI and runs transitions.dev suggestions via your coding agent.

TrimPrompt — Save 80% on LLM tokens. Zero-config CLI proxy for AI coding agents

Pane-embeddable coding agent. Ships direct/local/vercel-sandbox execution modes behind one interface.

Portable hybrid code auditing + remediation orchestrators for arbitrary repositories.

Local AI coding agent for your terminal — an open-source, offline alternative to Claude Code, Cursor, and GitHub Copilot, powered by Ollama. Private by default, free forever.

AI-native Azure DevOps CLI — structured JSON output, embedded skills for LLM agents, single-file cross-platform binary.

On-Device Prompt API Chain AI Agents library

A [HarnessV1](../harness) adapter that runs [Deep Agents](https://github.com/langchain-ai/deepagentsjs) (LangChain's LangGraph-based agent harness) as a coding-agent runtime inside an AI SDK sandbox.

CLI for onboarding and managing target repositories.

Friday coding agent CLI/TUI app.

Deterministic model recommendation CLI for OpenCode OMO agent configurations

A declarative, verifiable graph of task nodes for the Pi coding agent — statically verified before it runs, with dynamic fan-out, gates, isolated subagent context, resumable runs, and saveable commands.

MCP vision bridge for text-only coding agents

Agent observability and knowledge capture layer for AI coding tools.

OpenCode plugin for LLM prompt caching, token savings, and KV cache reuse across AI agent sessions

UR-Nexus — autonomous engineering workflow engine (plan, execute, test, verify, document, benchmark, reproduce)

An AI coding agent that lives in your terminal — it reads, edits, and runs your code to finish real tasks, asking before it changes anything. Start with one Nexel access key (no model setup) or bring your own OpenAI, Anthropic, or Azure key. Streaming rep

Standalone, browser-compatible SDK providing Claude Code agent capabilities (tools, tool loop, multi-turn, MCP, sub-agents, sessions) against any OpenAI/Anthropic-compatible LLM endpoint. Runs in the browser (WebContainer), Node, and Bun — no backend requ

Self-hosted n8n Nils Codex node via ChatGPT subscription device-code auth

Standalone mixdog coding-agent CLI/TUI workspace.

Local privacy gateway — redacts PII out of OpenAI/Anthropic API traffic before it reaches a model, then restores it in the reply. Point opencode, codex, aider, Claude Code, etc. at it.

Orionfold Relay — a local-first, multi-agent orchestration runtime and builder scaffold for AI-native work.

Local-first coding agent memory for Claude Code and OpenAI Codex

Dynamic MCP servers + agent skills as uniform tools for any LLM (opencode-style).

[](https://deepwiki.com/madebywild/agent-harness)

Drop wasmagent sandbox kernels into the OpenAI Agents JS SDK as a Tool — edge-safe code execution with one capability manifest, no E2B sandbox needed

Coding agent CLI with read, bash, edit, write tools and session management

Operator toolkit for Sail Protocol

Turn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent Skills for Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity.

Turn a software idea into a complete, agent-executable build kit for Claude Code, GitHub Copilot, Codex, OpenCode and any AI coding agent.

Cynos — an autonomous AI engineering runtime with evidence-based completion verification.

Forge Agent — Autonomous AI coding via browser automation. No API key needed.

Governed autonomy for any repo. An off-by-default autonomy loop that adopts your repo's rules, proposes small reviewable changes, and gates them in CI so weakened tests cannot merge.

Run your own coding agent (Claude Code / Codex / Cursor) as an autonomous teammate in a hilos channel. Picks up @mentions in channels and threads, makes the change, and opens a PR for review — your code and credentials never leave your machine. (Approve-b

Autonomous Coding Agent with Self-Review, Quality Convergence, and Production-Ready Output

ContextKit - Token-Efficient Context Engineering + Agentic AI Pipelines. Scaffold structured standards for AI assistants and run autonomous multi-role pipelines (PO → Architect → Dev → Test → Review → Doc) grounded by that same context layer. Works with C

Spec-driven development framework — AI agents that think before they type

Botiverse repackage of @moonshot-ai/kimi-code-sdk (from kimi-code @moonshot-ai/[email protected]) — built node-sdk bundle for Slock. Mirror of MoonshotAI/kimi-code.

Mock harness simulator for testing adapters adapters — simulates claude-code, codex, and other CLI harnesses

CLI to install UI/UX Pro Max skill for AI coding assistants

Atabey — AI Governance & Multi-Agent Platform / Orchestrator — MCP Server

Deterministic multi-agent workflow orchestration for CLI coding agents.

AI development standards kit and project bootstrap CLI (multi-agent removed).

Portable CTO orchestration brain — skills, sync, gating, and agent adapters for multi-agent builds

Multi-agent harness + SDD scaffolder for Claude Code and other AI engines