Artificial Intelligence

A safe, fast, flexible code analysis and parsing library built in Rust. High-level entry point for the Thread ecosystem.

Core AST engine for Thread - parsing, matching, and transforming code using AST patterns. Forked from ast-grep-core.

SDK for mini-chat: policy plugin traits, models, and errors

Train logisitic regression models for benign vs. malicious files based on byte n-grams and publish research, plus related tools.

Model training and fine-tuning for the Brainwires Agent Framework — cloud fine-tuning and local LoRA/QLoRA/DoRA training

Extensions and support for linear algebra in DataFusion

Language definitions and parsers for Thread

NER, coreference resolution, relation extraction, PII detection, and zero-shot entity types

Persistent, git-friendly memory storage for AI agents with hybrid semantic + full-text search

floDl — a flow-graph deep learning framework built on libtorch

Decapod is the daemonless, local-first control plane that agents call on demand to align intent, enforce boundaries, and produce proof-backed completion across concurrent multi-agent work. 🦀

Service layer interfaces for Thread

Bounded session management for MCP servers — max sessions, FIFO eviction, rate limiting

Local embedding generation using GTE-Qwen2-1.5B-instruct via Candle — private, on-device AI inference

Mini-chat module: multi-tenant AI chat

Encrypted agent-to-agent communication protocol library

A lightweight, configurable, local-first full-text search engine for Markdown knowledge bases with Japanese text support

Core data models and traits for Canon Protocol — verifiable, censorship-resistant knowledge sharing for AI

Procedural macros for stand-in MCP server framework.

Static audit plugin for mini-chat — logs audit events via tracing

Rule-based scanning and transformation engine for Thread

Core traits and types for descry-tool framework

Our mission is to be the default way developers create custom LLMs

MCP server for semantic memory — pure-Rust embeddings, vector search, git-backed storage

Run prediction functions in your Rust apps.

A standard way to declare and run agent containers for your projects.

Composable data sampling primitives for deterministic multi-source ML/AI training-data orchestration.

Procedural macros for descry-tool

SDK for the infer AI agent platform

Daemon for the infer AI agent platform

CLI for the infer AI agent platform

A generic, composable genetic algorithm framework for Rust

Permanent storage layer for Canon Protocol — censorship-resistant knowledge distribution via Arweave

Encrypted agent-to-agent communication daemon and CLI

Hybrid semantic+lexical RAG query engine with Merkle proof verification for Canon Protocol

mechanics automation framework (http server)

CLI validator for NotarAI spec files

Canon node ingestion pipeline — local-first AI knowledge management with anonymous sync

A lightweight CLI for managing long-running task graphs for coding agents.

A stand-in for your MCP server boilerplate.

Deterministic & Blazing-Fast Skills Manager for AI Agents (Claude Code, Cursor, Codex & More).