Dev & Engineering AI Agents

750 results
Dev & Engineering

Codex Autoresearch

Run measurable optimization loops inside your codebase: give it a goal, a benchmark, and a boundary, and it experiments, keeps evidence, and leaves a reviewable patch.

★ 836 FS 91 Strongly recommended 2d ago Apache-2.0
Dev & Engineering

Zoetrope

Watch a Claude Code session as a live flow graph — main agent, subagents and tool calls — in your terminal or browser.

★ 802 FS 89 Recommended today MIT
Dev & Engineering

elizaOS

An open-source TypeScript system for building, running, and extending autonomous AI agents.

★ 19k FS 88 Recommended today MIT
Dev & Engineering

Unlazy Completion Discipline

Keep AI agents from finishing early with deep decomposition, acceptance ledgers, and executable gates.

★ 3.2k FS 86 Recommended 4d ago MIT
Dev & Engineering

Pydantic AI Skills

Agent Skills support for Pydantic AI with progressive disclosure, remote skill registries, and sandboxed execution of bundled scripts — so your skill library can grow without bloating the prompt.

★ 369 FS 86 Recommended today MIT
Dev & Engineering

Better Harness

Diagnose and improve coding-agent workflows with verifiable evidence.

★ 2.2k FS 85 Recommended today MIT
Dev & Engineering

JS Reverse MCP

Continuous browser-side JavaScript debugging and replay for AI coding assistants.

★ 2.7k FS 82 Recommended 4d ago Apache-2.0
Dev & Engineering

Apache Maka

A local-first agent workspace that performs project work while preserving recoverable execution records.

★ 4.9k FS 82 Recommended today Apache-2.0
Dev & Engineering

Kungfu

Keep one body of work moving across agents, sessions, and failures.

★ 4.5k FS 81 Recommended 1d ago Apache-2.0
Dev & Engineering

NotebookLM Python Automation

Automate Gemini Notebook research, generation, and exports through Python, CLI, or coding agents.

★ 19k FS 81 Recommended today MIT
Dev & Engineering ✓ Google · Official

ADK Agent Recipes

Start ADK agent projects from small, runnable reference implementations.

★ 10k FS 81 Recommended 3d ago Apache-2.0
Dev & Engineering

Pilotfish Multi-Model Orchestration

Frontier models plan, cheaper models execute, and fresh-context verification guards quality — a one-prompt-install orchestration policy for Claude Code.

★ 683 FS 81 Recommended 10d ago MIT
Dev & Engineering

Osaurus

A native Mac harness for persistent, tool-using AI agents that can run with local or cloud models.

★ 7.8k FS 80 Recommended today MIT
Dev & Engineering

git-lrc Commit-Time Code Review

Automatically review Git diffs and surface risks before each commit lands.

★ 1.5k FS 80 Recommended 2d ago NOASSERTION
Dev & Engineering

Stately Agent

State-machine-powered LLM agents with XState: the machine owns control flow, the model only picks legal events, so invalid agent actions are impossible by construction.

★ 456 FS 80 Recommended today MIT
Dev & Engineering

Chrome DevTools MCP

Give coding agents direct Chrome automation, debugging, and performance analysis.

★ 51k FS 79 Use with care today Apache-2.0
Dev & Engineering

Harmonist

An IDE-hooked multi-agent workflow that enforces review, memory, and integrity checks for AI-assisted coding.

★ 2.3k FS 78 Recommended 3mo ago MIT
Dev & Engineering

Bernstein

Deterministically orchestrate parallel CLI coding agents with offline-verifiable run records.

★ 1.1k FS 78 Recommended today Apache-2.0
Dev & Engineering

LangWatch

Evaluate, test, trace, and monitor LLM applications and AI agents across development and production.

★ 3.5k FS 78 Recommended today Apache-2.0
Dev & Engineering

Gortex Code Intelligence

A local code graph that gives coding assistants precise context and cross-repository impact analysis.

★ 1.6k FS 78 Recommended today Apache-2.0
Dev & Engineering

Oh My Hermes (OMH)

A professional operating layer for Hermes Agent: per-model routing, parallel coding, 108 specialist skills, and reviewable long-term memory — install once, keep Hermes.

★ 1.5k FS 78 Recommended today MIT
Dev & Engineering

Surf CLI

A CLI that lets AI agents control Chrome — zero config, agent-agnostic, and battle-tested, so any agent that can run shell commands can drive the browser.

★ 612 FS 77 Use with care 1d ago MIT
Dev & Engineering

OpenHands Agent Canvas

A self-hosted control center for coding agents — run OpenHands, Claude Code, Codex, or any ACP agent

★ 87k FS 76 Recommended today MIT
Dev & Engineering

TanStack AI

Build type-safe streaming, tool-calling, and multimodal AI applications without committing the application core to one model provider.

★ 3.1k FS 76 Use with care 2d ago MIT