MCP servers and skills: search, filter by where they run, and compare.
Small, calibrated decision models on your own machine: systemone-compatible local server, 6 agent skills, Claude Code guard, MCP tools. Weights on Hugging Face.
PythonApache-2.0★ 21No key
Intent compiler for AI agents — converges vague requests into typed IntentSpec contracts (probe, ask, or halt before routing), the input layer for routers and typed-decision models like Jev & Laya
SkillMIT★ 763No key
System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics
PythonApache-2.0★ 149No key
Self-hosted MCP server and Jev-compatible HTTP API for small decision models (Laya, Julia-1, clef-flash) on one GPU, in Docker
DockerApache-2.0Few starsNo key
Agent skills for designing, training, evaluating and improving application-specific decision systems. Primitive/model selection, data assembly, export/reload and bounded hill climbing. TypeSafe Jev is
SkillMIT★ 12No key
Make the call. Run local Laya, Von, CLM or hosted Jev for typed classification and scoring through one HTTP and MCP API, with resource-aware batches.
DockerWTFPL★ 3Few starsNo key
Open schemas, recipes, templates, examples and agent tooling for Brida Reflex.
SkillApache-2.0★ 4Few starsNo key
女性高成就者决策智库 | Women High-Achievers Decision Intelligence — AI Skill for real-world decision support based on 22 real women's life cases. Works with Antigravity, Claude, and any AI agents.
SkillMIT★ 4Few starsNo key
TuringCorp Decider — MCP server discovery metadata (registry manifest, listing docs)
Hosted by authorMITFew starsNo key
pstack reworked for T3 Code: delegated subagents, worktree threads, PR watching, scheduled runs.
SkillMIT★ 155No key
Jev Browser — indexed browser automation. Jev chooses the control, Playwright acts. A CodexQA skill.
SkillMIT★ 51No key
Self-hosted memory server for AI agents. Share context across Claude Code, Codex, OpenCode, and ChatGPT over MCP.
GoMIT★ 72No key
Long-term memory for AI coding agents (Claude Code, Codex, opencode) as a tree of plain files
PythonMIT★ 37No key
Autonomous trading agents with deterministic execution. The agents propose; the system decides.
PythonMIT★ 36No key
Offline $0 decision layer for coding agents: Choice/Score/Noul primitives, BELKI confidence gatekeeper, ultra-planning, red-teaming, research and RLVR self-improvement -- as an MCP server + CLI + Clau
Node.jsMIT★ 4Few starsNo key
ASD-STE100-style plans for AI coding agents, inspired by Karpathy's 80% STE tip: Claude Code, Codex or Cursor writes a short plan you approve before it codes.
SkillMIT★ 8No key
Agent skill (Claude Code, Codex, Cursor, OpenCode, Hermes Agent and more): turn a process description into a self-contained, clickable HTML workflow diagram plus a PNG for slides.
SkillMIT★ 8No key
MIMIR is a non-generative decision model: give it a context, a question and the options, and it answers with a typed, calibrated decision, the evidence behind it, and a certified signal for when to ac
PythonApache-2.0★ 3Few starsNo key
Codex, Claude and Antigravity independently examine the same task, challenge each other across five rounds, and synthesize one supported decision.
SkillMIT★ 2Few starsNo key
A second opinion on your decisions, from a different AI company than the one you think with.
Node.jsMIT★ 1Few starsNo key
Open-source developer harness and runtime safety toolkit for AI coding agents powered by TypeSafe AI / Jev
Node.jsMIT★ 1Few starsNo key
Crash-test your AI agent on real professional decisions (MCP server)
PythonMITFew starsNeeds a key
Keeps your Mac roomy: finds what is safe to delete, warns before storage or memory runs out. CLI, TUI and MCP server for people and AI agents.
Node.jsApache-2.0Few starsNo key
Official JavaScript SDK and CLI for Rightis
Hosted by authorMITFew starsNo key
Who stands behind it
