Declarative management of Agent Skills on Nix

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.

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)

The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex & more. Build Clawdbot 🦞· APIs for Lovable · Bots for Slack & Lark/Feishu · Skills are infrastructure, not prompts.

[ICML 2026] Meta Context Engineering via Agentic Skill Evolution

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

AI agents and Nix: parametrable skills/instructions and tools, packaged together in a reproducible and modular fashion

Typed React command-center components, live examples, and a portable coding-agent skill.

Fluent argument validation for fluent software development.

LLM agents as your hyperparameter optimizer.

Preline UI is an open-source set of prebuilt UI components based on the utility-first Tailwind CSS framework.

Python toolkit, MCP server, and agent skills for reproducible, auditable clickstream and event log analytics. Helps AI agents, data scientists and analysts build, validate, and cross-check product analytics, quantitative UX, customer journeys, graph-based user flows, behavioral segmentation, A/B tests, process mining models, Markov chain simulation

Interactive documents from Markdown. Extends MD with forms, approvals, webhooks, and more — built for next gen apps

Computer-Use SDK for E2E QA Testing

Deterministic safety solutions for probabilistic AI agents

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace, to navigate, interact with, and extract information from web pages autonomously.

Markdown that runs — one file, any agent.

Write HTML. Render video. Built for agents.

Open-source customer money path for usage-based SaaS — authorize customer spend before paid work runs.

Implementation of Podlite markup language

Real time communication for agents. Wake on message, channels, DMs and actions. Useful for orchestrating agents.

🔬 A Researcher&Agent-Friendly Framework for Time Series Analysis. Train Any Model on Any Dataset!

Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.