griddynamics/
rosetta
griddynamics/rosettaHarnesses
An instruction layer for AI coding agent
344
OpenCoven/covenHarnesses
Local-first runtime for project-scoped AI coding-agent sessions, with durable state, authority boundaries, and multi-harness interoperability.
47
aliengiraffe/
vigilante
aliengiraffe/vigilanteHarnesses
Vigilante is a sandbox-first orchestration layer for coding agents. It isolates every task in a git worktree, enforces strict credential scoping, and gives you full audit logs — so your agents can't burn down production.
40
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
irahardianto/awesome-agvHarnesses
Comprehensive sets of standards and practices designed to elevate the capabilities of AI coding agents.
156
aisa-group/
skill-inject
aisa-group/skill-injectHarnesses
Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
96
CodelyTV/
agent-harness
CodelyTV/agent-harnessHarnesses
Our agent harness: Skills, plugins, hooks, and utilities to improve the quality of your agent.
261
dredozubov/hazmatHarnesses
Containment for AI agents - user isolation, sandboxed execution, network controls, backup/rollback. TLA+ verified.
173
AR6420/
Hail_Hydra
AR6420/Hail_HydraHarnesses
🐉 Hail Hydra — Multi-headed speculative execution framework for Claude Code. 10 AI agents, 3x faster, ~70% cheaper. Inspired by speculative decoding.
47