JCR · Jev Capability Resolver
Uses TypeSafe Jev to resolve deterministic commands from a nested capability tree for agent harnesses. Includes an MCP server, CLI, benchmark harnesses, and 50 benchmark scenarios.
OPEN SOURCE · CURATED REPOSITORIES
Curated Jev SDKs, tools, demos, integrations, benchmarks, and research projects. Repository metrics come from GitHub; titles, summaries, and categories are editorial.
Ranked by GitHub Stars
Ranked by recent Star growth and update activity
Uses TypeSafe Jev to resolve deterministic commands from a nested capability tree for agent harnesses. Includes an MCP server, CLI, benchmark harnesses, and 50 benchmark scenarios.
Unofficial CLI and Python tool to estimate token counts, cost, and context limits for TypeSafe System One / Jev API requests. Calibrated on real API responses and not affiliated with TypeSafe.
Provides evaluation and gateway tooling for TypeSafe Jev / System One-compatible decision models, including calibration metrics, threshold optimization, response validation, rate limiting, caching, circuit breaking, and audit logs. Community software independent of TypeSafe AI.
A one-stop kit for TypeSafe Jev: provides a Python CLI and MCP server for Jev/System One judgments, with commands for verify, screen, classify, extract, match, route, ask, find, rerank, compact, and batch, plus prompt libraries and plugin setup for Claude Code/Codex.
jev-assist is a coding-agent skill that uses TypeSafe Jev/System One to rank repository files by task relevance, detect convention drift, and flag risky diffs before commit. It includes setup, validation, and pre-commit hook wiring.
A developer toolkit for TypeSafe System One/Jev with a SysOneScript language, Go client, semantic code checks, and Studio.
An MCP-first developer toolkit for TypeSafe/Jev System One, including CLI, MCP server, evaluation packs, audits, and Prometheus metrics.
Scans LLM logs and code for decision-shaped calls, estimates savings from migrating to JEV, calibrates decision models, and generates migration PRs. Optionally calls the JEV API for a self-audit.
Unofficial toolkit for TypeSafe's Jev/System One model, providing a static linter, shared record format, and testing, drift, benchmark, and calibration tools.
A Ruby linter that reads YAML rules phrased as plain-language questions and asks TypeSafe AI's Jev model to judge each file, reporting offenses based on the model's noul probabilities. Supports CI, pre-commit, and local runs.
A browser form for building requests to TypeSafe's Jev. Pick a template, fill in the blanks, copy the request; no JSON or install needed, runs locally.
A local-first macOS app, TUI, and CLI for managing AI coding tool skills, with optional TypeSafe Jev recommendations.