Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTTP API. Works with Cursor, Claude Code, Codex, and any MCP-compatible agent.

Repository-first deterministic migration and atomic Skill source for Claude Code and Codex.

Deterministic safety solutions for probabilistic AI agents

Deterministic prose checks for clearer coding-agent responses

Beautiful App Store screenshots — perfect to spec, shipped end to end. An open-source skill for Claude Code & Codex: deterministic HTML panels, one-pass translation, AI sticker art, spec-preserving makeovers.

HAR: open agent harness (CLI + MCP) for coding agents. Isolated worktrees, deterministic verify, software factory workflows for Claude Code, Cursor, and Codex.

Local-first static analysis that turns source code into deterministic, source-grounded workflow maps for coding agents via MCP.

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

Deterministic research MCP server on FastMCP 3 — 5-engine web search, 9-platform social search, 6 academic DBs, news aggregation, entity profiles, conflict detection, document analysis. No API keys. No in-server LLM. Structured outputs for agent chaining.

Run Linux-style commands on Windows via deterministic bash→PowerShell translation. No VM, no WSL. MCP server + CLI built for AI agents (Claude Code, Codex, OpenCode...). GNU-style output, bash-style errors, UTF-8/GBK handled.

Vestige enhances agents by deterministic root-cause retrieval that reaches backward through time to find the quiet change, decision, or service that caused today’s failure, not the lookalike.

Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

German AI Text Humanizer for Claude Code & Codex. Audits 72 German AI-writing patterns using deterministic linters and evidence-safe rewrites. No fact-bending, no bypassing tricks.

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deterministic spec passes, and there is no "done" without live acceptance evidence. Spec-first, verification-gated, forbidden-paths enforced.

Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents.

Write HTML. Render video. Built for agents.

Isometric games made easy — an agentic game kit. 12 agent skills over 9 zero-dependency TypeScript packages. Type one sentence, get a playable game.

Governance standard and reference toolset for LLM-maintained knowledge corpora

Compile, verify, and run multi-agent DAGs across Pi, Codex, Claude Code, OpenCode, and Grok—with resume, replay, and incremental recomputation.