Sandbox

20 repos for “exe” · Harnesses · TestingClear

Sort

coleam00/

dark-factory-experiment

coleam00/dark-factory-experimentHarnesses

A repository that ships its own code. AI workflows triage issues, implement them, review, and auto-merge with no human reading the diff. Runs on Archon. The app it maintains is a cited RAG chat over YouTube transcripts, live at chat.dynamous.ai.

151

code-yeongyu/

lazycodex

code-yeongyu/lazycodexHarnesses

The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.

3.4k

joe960913/

Jixu

joe960913/JixuHarnesses

Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.

100

LarsCowe/

bmalph

LarsCowe/bmalphHarnesses

Unified AI Development Framework - BMAD phases with Ralph execution loop

406

AMAP-ML/

LongHorizon-Harness

AMAP-ML/LongHorizon-HarnessHarnesses

The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.

1.5k

a5c-ai/babysitterHarnesses

Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration

1.8k

dredozubov/hazmatHarnesses

Containment for AI agents - user isolation, sandboxed execution, network controls, backup/rollback. TLA+ verified.

173

parcadei/

Continuous-Claude-v3

parcadei/Continuous-Claude-v3Harnesses

Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.

3.9k

Taoidle/

plan-cascade

Taoidle/plan-cascadeHarnesses

AI-powered cascading development framework. Decompose complex projects into parallel executable tasks with auto-generated PRDs, design docs, and multi-agent collaboration (Claude Code, Codex, Aider).

140

chaitanyagiri/

munder-difflin

chaitanyagiri/munder-difflinHarnesses

A local multi-agent harness that works with your existing Claude Code, Codex subscriptions, allows you to run an office of agents

6.8k

peakmojo/

agentic-mcp-client

peakmojo/agentic-mcp-clientHarnesses

A standalone agent runner that executes tasks using MCP (Model Context Protocol) tools via Anthropic Claude, AWS BedRock and OpenAI APIs. It enables AI agents to run autonomously in cloud environments and interact with various systems securely.

spring-ai-community/

spring-ai-playground

spring-ai-community/spring-ai-playgroundHarnesses

Safe local execution layer for AI agent tools. Build, validate, and publish MCP tools with a no-pass-no-run workflow — cross-platform desktop app powered by Spring AI.

137

AbyssCN/

oh-my-dag

AbyssCN/oh-my-dagHarnesses

The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside the model — exit codes, write-set checks, and a cross-family verifier. MCP server, 50 tools, bring your own models.

digipulse-engineering/

GAAI-framework

digipulse-engineering/GAAI-frameworkHarnesses

Turns AI coding tools into reliable software delivery systems. Drop a .gaai/ folder into any project — Discovery defines what to build, Delivery executes autonomously until criteria pass. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, and more. No SDK. No package. Markdown + YAML + bash.

160

UiPath/coder_evalHarnesses

Playwright for coding agents. Benchmark Claude Code, Codex, Gemini, and OpenCode on your own tasks - and test that your skills, MCP servers, and CLIs work when an agent uses them. Sandboxed YAML suites, activation checks, A/B experiments, CI gates.

127

github/

gh-aw