by lxe
Pocket Model from your terminal and your agent: find the smallest model that does your task, train it on your data, and serve it. CLI and MCP server.
npm:pocketmodel · local package12/wkpublished 23 d ago
Model access, evaluation and agent infrastructure.
Pocket Model from your terminal and your agent: find the smallest model that does your task, train it on your data, and serve it. CLI and MCP server.
Local MCP server for the Unbox Gov Greek public procurement datasets (organizations, contracts, contract items, detection flags) on HuggingFace.
Beautiful visual workspace manager for Claude Code. Access 136+ professional templates, automate workflows with hooks, and manage your AI development environment through an elegant web interface.
Client-side tooling for a Robinhood Trading MCP connection: enumerate and diff the live tool surface, and enforce policy guardrails on agent-initiated writes before they leave your machine.
Preflight checks for AI coding agents — catch vague prompts, surface missing context, search session history
One-key prompt enhancement — turn vague ideas into structured task specs anywhere you type to an AI. CLI + MCP server. Zero dependencies, BYOK, offline-capable (Ollama).
AI coding-agent skill for shipd.ai Olympus submissions: design hard tasks, write hidden tests, avoid Docker traps, and verify locally.
MCP server for LeadVal — submit finished AI-agent conversations for scoring, poll them to a terminal state, and ask mid-conversation whether this workspace already knows the person you are speaking to. Four tools over stdio for Claude Desktop, Cursor or y
Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
Markdown resume builder that lints your CV and explains why it will not fit two pages. ATS-safe PDF, job-description tailoring, CLI + MCP server for AI agents.
Skill-discovery prompt builder for coding agents. Turns vague tasks into expert prompt text that searches local and ecosystem skills, recommends install/load steps, and tells the next agent which specialist skills to invoke and what evidence to collect. O
Inspect MCP servers and write a local readiness report.
MCP server for ThinkHive Explainer API v3 - Run-centric architecture with facts vs inferences, deterministic linking, calibrated predictions, and AI agent observability
Public AI operations templates and a starter MCP server for human-reviewed AI operations.
Let Claude plan and validate coding tasks while OpenCode CLI, driven by a free model, does the implementation. CLI + MCP server.
Ask huge PDFs, Word documents and spreadsheets specific questions: your AI gets only the passages that answer, with citations. A local MCP server for Claude Code, Cursor and Codex, plus a browser version.
Give your AI agent a signed, verifiable identity in one line.
MCP server that carries what one session learned into the next. A per-project ledger written as things happen, scored per task by TypeSafe's Jev evaluation model via the Vercel AI Gateway.
Turn Claude Code into a senior AI software engineer: skills, subagents, slash commands, and engineering conventions, scaffolded with one command. A pragmatic alternative to spec-driven development.
Production-grade, cross-platform agent meta-skill for autonomous capability discovery & two-pass prompt optimization.