Zero-dependency System One decision harness: 5 semantic gates saving frontier AI agent tokens on trivial errors & doom loops. Python + TypeScript + Rust. MCP-compatible.
⚡ Jev Harness: The Token Optimizer & Decision Gate for AI Coding Agents
Stop burning 50,000 frontier tokens on missing packages, network flakiness, and circular doom loops.
jev-harness is an ultra-fast, zero-dependency token optimizer, test failure triage gate, and semantic guardrail for AI coding agents (OpenCode, Command Code, Claude Code, Cursor, Antigravity IDE, Windsurf, Zed, and Pi). Powered by TypeSafe AI's Jev System One non-autoregressive decision model.
🤖 Operating as an AI Agent? You MUST read AGENTS.md (Português) before executing tasks, and refer to our Universal AI Agent Integration Guide to plug the harness into any project in 2 minutes.
When an autonomous coding agent encounters a test failure or compiler error, the standard reaction is to dump 500 lines of raw traceback into an expensive frontier reasoning model (GPT-6 Astra, Claude Fable 5.1).
Failure Scenario Without Jev Harness With Jev Harness :--- :--- :--- Missing dependency (ModuleNotFoundError, Cannot find module, TS2307, E0463) 💸 50,000 LLM tokens burned (~$0.50 - $2.50) + 15s delay to output pip/npm install ... ⚡ Jev triage in 90ms ($0.00004) → Action: install package deterministically. 0 LLM tokens. Flaky transient error (network timeout, port busy, ECONNREFUSED) 💸 LLM hallucinates architectural changes to "fix" an ephemeral glitch ⚡ Jev detects flaky transient → Auto-retry worker once. 0 code changes. Circular refactoring (Doom Loop: attempting the same fix 3+ times) 💸 200,000+ tokens burned in endless circular loops 🛑 Jev Abort Gate triggers (exit 1) → Stops loop, alerts developer. Trivial
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/ismaelsoilet--jev-harness.html)
Hand a whole browser task off in one call: a decision model drives the page server-side, so a flow costs one call, not a turn per click. Ref-based element tables, code-checked assertions, zero-model m
00200200/usagetrimKeep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.
TeodorMCP/universal-connector-mcpUniversal MCP server: connect any OpenAPI/Swagger, GraphQL, gRPC or SOAP API to AI agents. Security-first, local, token-efficient. Any API. One server.
thaildhe172591/pythiaPL/SQL development for AI agents on Oracle Database - expert queries, impact analysis, and a snapshot-verified write path with honest rollback
nettanvirdev/inertiainertia-ai: a desktop workspace for AI agents. Chat, built-in tools, MCP and OpenAPI integrations, Docker/Daytona sandboxes with a live desktop, routines and memory. Bring your own model and keys.
LukeHawkins/turbofigLet AI drive Figma. Instant, lightweight and free: no paid Figma seat, no quota, no Figma token. Open source, for macOS.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.