Superfast runtime validators with only one line

Claude Code / Codex / pi plugin that hands the agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM.

HeartFlow (心虫) — AGI Layer 1: the Discriminator. Rule-based engine that checks what AI says before it reaches humans. 46 discrimination dimensions, 9-layer pipeline, 137 modules (logic/decision/cognition/emotion/memory/ethics/collaboration), 179 MCP tools

Traceloop Software Development Kit (SDK) for Node.js

DeepSeek Harness provider adapter for Codex subscription compatible Responses endpoints

Your agent writes bad React. This catches it

Core framework for media pipeline orchestration — types, execution engine, validation, quality gates, artifact registry, and mock provider

LLM capture proxy with Anthropic cache_control TTL stamping, vision handoff, concurrency gating, rate limiting, and a live inspection dashboard

Extraction/Slicer — chaos documents → governed SE-graph candidate slices (slicer → auto-typing → suggestion-gate)

JavaScript obfuscator

MediaPipe GenAI Tasks

PostgreSQL schema-aware deployment control — idempotent SQL migrations with CI-enforced integrity checks, expand/contract migration orchestration, schema drift detection, and unified gating across database, application, and infrastructure rollouts

Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference

To get the docs for the LLM, check out [this index](./llm/index.md).

To get the docs for the LLM, check out [this index](./llm/index.md).

Lightweight, composable agent orchestration for autonomous agents. Multi-agent primitives (spawn, defer, MCP meta-tools), single-gate governance via an optional bareguard peer, cross-platform shell tools, MCP bridge. Zero required runtime deps.

Codebase intelligence for TypeScript and JavaScript: health, complexity, duplication, architecture, styling drift, and unused code from one graph. CLI, LSP, and MCP server. Zero config for over 100 frameworks.

Advanced mathematical AI interpretability: Category Theory, Homotopy Type Theory, Spectral Analysis, Causal Inference, Quantum Topology, and Sheaf Cohomology for WebAssembly. Implements functorial retrieval, univalence axioms, Cheeger bounds, do-calculus,

Nx-specific webpieces validation rules and graph tooling. Bundles all @webpieces rule packages with Nx graph validators and an inference plugin.

DeepSeek Harness plugin: /logs command and a stderr log exporter, so ctx.logger output is actually visible