Babel plugin that compiles spectypes validators
48-tool MCP server for codebase analysis — dependency graphs, architecture layers, security scanning, refactor plans, git history, and more. Works with GitHub and GitLab repos (cloud + self-hosted) and local directories.
Patchwork - Manage patches on top of upstream repositories
Forge CLI — AI-native developer framework. Scaffold, lint, scan, ship.
Evaluate a Javascript expression
Latency monitoring, SLA enforcement, and optimization analysis for agent-eval-harness
Open source AI evaluation framework — LLM-as-judge + assertion-based evals for any AI app. CLI + MCP server.
Quality gates and CI/CD regression checks for RAG evaluations
Orchestrated evaluation suite runner with results aggregation for agent-eval-harness
A CLI for developing, managing and publishing tscircuit code (the "npm for tscircuit")
A sandboxed eval().
Provider-agnostic LLM-as-judge with calibration and consensus for agent-eval-harness
eval-genius enables evals of arbitrary async code. It is generally intended for making multiple assertions on outputs which are generated nondeterministically. These assertions can be used to score algorithms on their effectiveness.
Command-line tool for detecting vulnerabilities in files and directories.
Lits is a pure functional programming language implemented in TypeScript
Evaluate RAG pipelines: retrieval precision, faithfulness, answer correctness. Multi-provider judge (Claude/OpenAI). Zero-config CLI.
Ad-hoc JSON-like comparison
Eval framework for Copilot CLI skills
Tool-use validation (selection, schema compliance, result verification) for agent-eval-harness
//command to exec the server in the cient
Mathematical expression evaluator
Hissab CLI — natural-language calculator in your terminal, powered by the Hissab engine
Simpl JSON rules engine
Golden trajectory management, comparison, and curation for agent-eval-harness