OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

Public results and task definitions for FrontierHarness Eval

[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

The evaluation benchmark on MCP servers

Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.

Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters

Open-source local-first cognitive memory. AGM-compliant belief revision (49/49 postulates). When a fact changes, downstream beliefs are automatically re-evaluated, not just flagged.

1688 CLI is an AI-agent-friendly command-line tool for 1688 sourcing, product research, supplier evaluation, procurement Inquire, and order management.helping dropshippers and Amazon sellers automate and streamline their sourcing workflow from 1688.

The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.

Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task

AgentVitals Checkup (/checkup) — an AI agent skill that gives your agent a professional health checkup: dual-axis Stability + Welfare scoring, a personality-style title, and a public cross-platform leaderboard. One-line install for Claude Code / OpenClaw / Codex / Coze. Bilingual EN/ZH.

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server