Sandbox
18 repos for state · TestingClear
heal-dev/
heal-playwright-tracer

Open-source statement-level Playwright tracer, purpose-built for AI agents. Analyzes test runs with increased accuracy.

45

Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.

414
satelliteoflove/
godot-mcp

Give your AI assistant eyes and hands in the Godot editor: scene editing, input injection, deterministic playtesting, and live game state for agents

159
AMAP-ML/
LongHorizon-Harness

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
remorses/
playwriter

Chrome extension & CLI to let agents control your browser. Runs Playwright snippets in a stateful sandbox. Available as CLI or MCP

3.9k
AVGVSTVS96/
better-github-skill

Optimized GitHub skill for coding agents: fewer tool calls, less context burned, lower cost, faster answers. One bounded call each for PR state, review threads, and CI failures.

49

Generate clean 2D game sprites & animation atlases — component-row pipeline: state rows, alpha cleanup, frame extraction, runtime atlases. Codex/Claude skill.

1.1k

Local-first runtime for project-scoped AI coding-agent sessions, with durable state, authority boundaries, and multi-harness interoperability.

47
parcadei/
Continuous-Claude-v3

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

The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.

188
zhnt/
loushang
zhnt/loushangHarnesses

AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.

1.4k

CoCo Super Intelligence is the orchestration layer that turns Claude Code, Cursor, or Codex into an engineering department: a routed advisory board, 185 skills, 280 commands, persistent state. Local. Open-core — MIT core; Super Intelligence is proprietary, own-use.

220
aplavin/
julia-mcp

MCP server for persistent Julia sessions — fast iteration without startup/compilation overhead

86
evalstate/fast-agentFrameworks & SDKs

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

3.9k
Epistates/
turbomcpstudio

A native desktop application for developing, testing, and debugging Model Context Protocol servers.

37