whereismyai
Tetriz Harness
Tetriz Harness: CLI and control plane that analyzes AI coding harness configurations, recommends improvements, and distributes approved artifacts to developers.
Tetriz Harness manages the rules, skills, agents, commands, hooks, and MCP configurations that guide AI coding tools such as Claude Code, Codex, Cursor, and Kiro. It features an on-disk scanner that checks local repository files for missing path references, dead pattern matches, and over-broad permissions. Its recommendations engine pairs with the tetriz-py service and a Gemini API key to propose new artifacts based on session analysis, review themes, and security signals. Approved artifacts can be distributed to specific developers, teams, or test cohorts using the included Go server, React admin UI, and Node-based harness-agent.
Tetriz Harness at a glance
Key features
- Scan repository harness files for broken references, conflicts, and loose permissions
- Generate recommended rules, agents, and hooks using Gemini and coding signals
- Persist scan findings, signals, and harness inventory records to PostgreSQL
- Distribute approved artifacts to user tool directories and known repository checkouts
- Target artifact rollouts to specific individuals, teams, or entire organizations
- Monitor per-person delivery and installation statuses via a React admin UI
- Run manually managed test and control rollouts to evaluate configuration changes
- Support coding agents including Claude Code, Codex, Cursor, and Kiro
Use it for
- Fix broken paths and permission flaws in team AI coding configurations
- Generate custom rules and hooks informed by team code reviews and session analyses
- Distribute unified skills and instructions across developer environments and local repositories
- Conduct test and control rollouts of coding configurations to measure workflow impact
Alternatives to Tetriz Harness
- Better Harness — Gathers project evidence and turns concrete gaps into prioritized findings.
- DeepSeek Harness — Builds on a plugin architecture to organize documents, analyze tables, and write code.
- Harness Meta-Skill — Generates specialized agent teams and skills for Claude Code from a single prompt.
- HarnessRouter — One API to manage agent runtimes, sandboxes, and execution lifecycles.
- Harness Manager — Manages your entire AI coding stack in one native Mac app.
- Claude Code Harness — Enforces a disciplined delivery loop with verification gates and safety checks.
- Langgraph Harness — Autonomous GitLab integration with secure sandboxed execution and persistent memory.
- Tetriz Engg Intelligence + Connectors — Offline Go packages join AI session logs, pull requests, and tracker issues.
- Fusion Harness — Run 2 to 5 models simultaneously against the same working directory with a single-writer invariant.
- LongHorizon Harness — Maintains durable task state and executes reliable, verifiable workflows over many hours.
- ZCode — Integrates GLM-5.3 with multi-agent workflows and remote chat control.
- Harness Engineering — Improves agent output by shaping the environment with context and tools.
All Tetriz Harness alternatives