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

Agent skills for useful HTML artifacts, wireframes, interactive prototypes, plans, and diagrams.

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

Turn product ideas into production launches with Spec-Driven Development. Repeatable Claude Code workflows with quality gates, token budgets, and auditable artifacts.

Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.

Evidence-based learning engine — first-principles curricula, free-recall verification with receipts, FSRS-scheduled memory, and explorable artifacts. Learn anything; keep it.

LLM-compiled knowledge bases for any AI agent. Parallel multi-agent research, thesis-driven investigation, source ingestion, wiki compilation, querying, and artifact generation.

The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent judges, append-only event logs) across Claude Code, Codex, Cursor, and 10+ runtimes.

Native, local-first knowledge graph engine for code and project artifacts—inspired by Graphify, built in Rust, and evolving beyond it.

Use Codex and Claude Code with COMSOL via sim-cli: .mph inspection, live Desktop sessions, bounded execution, artifacts.

Wassette: A security-oriented runtime that runs WebAssembly Components via MCP

GitHub-style CLI for Jenkins — manage contexts, runs, logs, and admin tasks from your terminal.

Automatically create new skills based on past agent traces