Code agents

DB Entity JSON generator from frontend project codebases

Scaffold a new theslop.ai agent: pick your runtime (Anthropic+Cloudflare, OpenAI Agents SDK, Claude Code, custom), inject the editorial role, get a tailored README + system prompt + .env.example + a memory/ tree shaped for the routing-index pattern.

Persistent memory + tool-result intelligence for AI agents — TypeScript SDK. One install, all framework adapters, MCP server, CLI, and the agent skill.

Cut AI Agent token costs by 96%. Chains multiple tool calls into a single TypeScript code execution in a secure sandbox.

Policy enforcement and rollback for AI agent code edits

A powerful Node.js agent tools

Workstation server for tiflis-code - manages agent sessions and terminal access

Complete Agentic GPU Infrastructure for Claude Code — 192 MCP tools: Full training lifecycle, inference deployment with cost guardrails, Ray cluster management (Wide-EP, disaggregated P/D, parallelism strategy), vLLM lifecycle (start/stop/sleep/wake/infer

A general-purpose coordination protocol and CLI for multiple AI coding agents working on one repository.

Deprecated — use agentassert-abc[claude-code] instead.

Agentic Environment & Resource Orchestrator

Make full use of every coding-agent subscription you pay for: a local CLI + MCP server that surfaces live usage limits and offloads work to providers with headroom.

Visual stepper UI for agentrr record-and-replay

Essential CLI tools for AI agent developers

RAG pipeline for Claude Code — indexes your codebase and exposes it as an MCP server

Agentic RAG MCP Server — 13 retrieval/read tools plus workflow help for AI-driven multi-round retrieval over any text

Run Anthropic Claude Code as an optio task; local subprocess or remote via SSH; ttyd-served TUI iframe.

Rule Coherence Graph — detect conflicts in AI agent rule corpora.

Placeholder — under active development.

VibeCode review: compare features, pricing, use cases, access model, and alternatives for this Mobile App Builders agent in 2026. Full-stack platform for building apps effortlessly with AI.

TakoCode — a Claude Code fork wired into the TakoFlow desktop agent

AI coding assistant CLI built on Robota SDK

Run Claude Code agents overnight on your codebase. Interactive terminal UI (Ink) + bash harness + Claude Code skill + slash commands. Write a todo file with Implementation+Validation pairs, launch, wake up to validated code.

Unified CLI for the @glrs-dev ecosystem — OpenCode agent harness dispatch + worktree management.

Zero-setup grounded web research MCP server and Pi extension for AI coding agents.

MCP server wrapping MiniMax AI as autonomous code executor with agent loop for Claude Code

MCP server for Godot Engine integration

Multi-agent orchestration for AI coding agents — spawn workers in git worktrees via tmux, coordinate through SQLite mail, merge with tiered conflict resolution. Pluggable runtime adapters for Claude Code, Pi, and more.

A small open-source CLI for orchestrating multi-agent Claude Code swarms. Filesystem-coordinated, no GUI, no MCP, no subscription.

OpenCode plugin for multi-agent swarm coordination

Multi-agent orchestration for AI coding agents — spawn workers in git worktrees via tmux, coordinate through SQLite mail, merge with tiered conflict resolution. Pluggable runtime adapters for Claude Code, Pi, and more.

Production-grade AI coding toolkit — 70 agents (incl. devil-mode adversarial crew), 194 skills, 97 commands, parallel multi-agent commands, semantic intent routing, self-learning memory, and a built-in MCP server (16 tools / 6 prompts / 377 resources) tha

OpenCode plugin for AWS Solutions Architect assistant with multi-agent Guru system

Docs-first engineering discipline for agentic coding assistants

CyberMind CLI — fullstack agentic coding assistant

MCP server implementation for agentic knowledge guidance system

Repo-local tending infrastructure for safer agentic engineering.

AI-powered security team-in-a-box. Multi-agent security testing platform with AutoGen-style orchestration.

AST+vector context router for AI coding agents — cut token costs 5-15x

Offline personal assistant MCP server — memory, tasks, contacts, and conventions stored locally in your Obsidian vault. Works with Claude Code, OpenCode, and any MCP-compatible agent.

Know what your agents cost. Cost intelligence for AI coding agents.

BrainPalace - Typed-memory & retrieval engine for AI agents (BM25 + vector + GraphRAG); code & docs today, more domains coming

Audit chain for Claude Code workflows — consensus verification, persistent memory, and XRPL provenance for every agent action.

企业级全栈代码助手智能体 - 多智能体协作架构

Time-travel debugging for LangGraph agents — record, replay, fork, and catch regressions from a single SQLite file.

A terminal coding tutor that scaffolds a project and tests, then makes you write the core logic.

Zero-config LLM API inspector — intercepts calls, shows token breakdown and cost estimates in a local dashboard

Portable, stdlib-only guardrail for autonomous coding agents — safe continuations instead of reckless actions.

Sync Pi coding agent models.json with models served by a vLLM/llama.cpp server

Runtime token proxy + optimization toolkit for LLM developers and enterprises. Intercepts API calls, strips waste in real-time, tracks costs, and serves a web dashboard.

cubic uses AI to review code, speeding up PRs and catching bugs quickly.

Neo Skills: A Universal AI Agent Skills Extension

Unified history of AI agent sessions across devices

AI agent platform and MCP server — knowledge packs, AI agent tools, workflow automation, and CLI

Mounaji AI agent skills — installable skill definitions for VS Code Copilot and compatible AI agent runtimes.

Mobile remote control and local agent mesh for the Pi coding agent. Pair your phone via QR over a relay, watch tool calls in real time, run multi-Pi sessions over a local Unix Domain Socket broker, and let agents talk to each other through structured requ

AI-powered code review tool that works as a LangChain Tool, powered by Groq.

Open-source Agent SDK. Runs the full agent loop in-process — no local CLI required. Deploy anywhere: cloud, serverless, Docker, CI/CD.

Config-driven autonomous Nx agent harness — multi-cycle state machine with Zod validation, git scope enforcement, and self-healing fix injection.

Persistent autonomous goals for pi — /goal loops until complete, paused, or budget-limited

CLI tools for Directive — AI coding rules, scaffolding, and more.

Auto-configuring AI agent framework that learns your codebase and builds itself

Agentic CLI for developers — OpenAI-compatible models, MCP, Skills

5 AI agents (Spec Author / Test Gen / Coder / Reviewer / Curator) for GHIaK Agentic — collaboration layer on GitHub Issues.

Spec-first project OS for agentic development — tasks, specs, work sessions, operational insights, and a synthwave TUI

An agentic coding CLI for DeepSeek models, in the spirit of Claude Code

Sagaz AI orchestration ecosystem installer for Codex Desktop.

gojaja (过家家) — file-system coordination layer for multi-LLM-agent collaboration (Codex, Claude Code, Cursor, ...). Let your agents play house on a shared codebase.

Unofficial local-first diagnostic CLI for NVIDIA NIM developer workflows.

Agent MCP Router MCP — one router for the whole MEOK fleet. Holds 62 MEOK MCPs behind one namespaced endpoint. Install ONE thing, get all of them. By MEOK AI Labs.

Agent Replay Debugger MCP — record every agent step + replay deterministically. Step-debugger for agentic loops. Audit-evidence signed exports. By MEOK AI Labs.

Approve or deny your AI coding agent's risky commands from your phone, with an audit trail. Works with Claude Code and OpenAI Codex.

Low-code framework for generating agentic AI systems from a prompt or spec

PreCompact ledger and per-component context profiler for Claude Code

Detect and revive Claude Code remote-control connections

Session checkpoint and recovery layer for Claude Code — resume interrupted sessions, export shareable HTML traces.

Native LangChain chat models for OpenAI Codex subscription OAuth and OpenCode Zen/Go — no Node sidecar.

LlamaIndex tool spec for the Ejentum Reasoning Harness. Wraps the hosted Ejentum MCP server and exposes eight cognitive harness tools as LlamaIndex FunctionTool objects: four dynamic (reasoning, code, anti-deception, memory) plus four adaptive variants (adaptive-reasoning, adaptive-code, adaptive-anti-deception, adaptive-memory) that pre-fit the cognitive operation to the caller's task via an adapter LLM.

Standalone observed-fact graph substrate for code and document structure

Point your agent at your docs and your RAG app; get a golden test set + an LLM-as-judge & retrieval scorecard, in one command.

The Best AI Agent Harness

Universal synchronization layer for AI agent orchestrators

Cray Code - A powerful AI agent framework with MCP, Skills, and Sub-agent support

AI Agent Orchestrator - Manages agile software development teams of AI agents

Maroo Agent Wallet Stack — MCP server for AI agent wallet management on Maroo chain

ONE Agent - AI agent with a code execution RAS.

Kodwai CLI — AI-agent coding challenges and interview sessions

AI agent platform for ClawBridge Agency, powered by OpenAI Codex. Self-hosted, secure, customizable.

Platform-agnostic nxtlinq AI Agent core — API client, types, and orchestration ports

AI Agent Hub MCP Server

The Universal Hub and Multiplexer for AI Agent MCP Servers and Skills

General-purpose agent with transport abstraction, state management, and attachment support

Give pi a mind: portable, self-maintaining memory for pi-coding-agent. Memory is passive — writes are explicit (remember_this / observe), retrieval is hybrid (vector + FTS5 + KG). Ships ask-first skill authoring (create_skill / update_skill).

Extentos MCP server — deterministic tools for building smart-glasses apps with AI agents.

ESLint rules that catch the patterns LLM agents get wrong — and teach them to self-correct

Installable oper8r Agent Skills for MCP clients, Claude Code, Codex, and Cursor.

Readonly technical support agent for Xuda Network mentors. It can inspect /var/xuda on the dev server through Codex with strict safety limits.

TrackJS Error Tracking agent for NodeJS

Universal MCP server for 8+ AI platforms. Connects Claude, Cursor, VS Code, Windsurf, Zed, Codex, and Gemini to 298+ AgentPMT tools.