Artificial Intelligence

Client library and tooling for the Hugging Face Xet data storage system.

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

Async runtime, configuration, logging, and utility infrastructure for the Hugging Face Xet client tools.

Client library for communicating with Hugging Face Xet storage servers. Use through the hf-xet crate.

Data processing pipeline for chunking, deduplication, and file reconstruction; used in the Hugging Face Xet client tools. Intended to be used through the API in the hf-xet package.

Core data structures including MerkleHash, metadata shards, and Xorb objects.

Low-level, generic LLM provider abstraction for Rust

Compatibility umbrella crate re-exporting awaken

Reverse engineering assistant that uses a locally running LLM to aid with pseudocode analysis.

A Rust framework for building AI agents from YAML specifications with trait-based extensibility

A2A v1.0 protocol wire types and helpers for Awaken

Phase-based execution engine, plugin system, and agent loop for Awaken

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

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

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

Ling - The Omniglot Systems Language

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

Glob and regex pattern matching for tool IDs in Awaken

Storage backends (memory, file, PostgreSQL, SQLite mailbox) for Awaken agent state

Server-driven UI component plugin (A2UI) for Awaken

Model Context Protocol (MCP) client plugin for Awaken

Extensions and support for linear algebra in DataFusion

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

Ultra-low-latency and high-throughput typed transport for multiprocess SHM and mmap. Layers framing, codecs, typed zero-copy, and inference-fabric topology helpers on disruptor-mp's LMAX-Disruptor-style ring substrate.

Cryptographically-sealed AI decision records with provenance, audit, and compliance. Court-admissible inference logging for LLM accountability.

AI-powered macOS automation agent using AppleScript, built with Rig and Ollama

Decapod is a Rust-built governance runtime for AI agents: repo-native state, enforced workflow, proof gates, safe coordination.

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

Skill package discovery and activation plugin for Awaken

OpenTelemetry observability plugin with GenAI semantic conventions for Awaken

Permission plugin with allow/deny/ask policies for Awaken tool execution

Production AI agent runtime for Rust — type-safe state, phase execution, multi-protocol serving

Cloud fine-tune APIs (OpenAI, Anthropic, Together, Fireworks, Anyscale, Bedrock, Vertex AI) + dataset pipelines for the Brainwires Agent Framework. Local LoRA/QLoRA/DoRA fine-tuning and training-from-scratch live in the sibling `rullama` workspace (`rullama-finetune`, `rullama-training`).

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

On-device inference engine for Apple silicon.

A composable, deterministic text data pipeline for ML. Ingest, denoise, chunk, split, and sample multi-source corpora into reproducible training triplets.

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

Core types, traits, and state model for the Awaken AI agent runtime

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

Proc macros for symbiont hot-reloadable function declarations.

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

Reusable debug/demo runners for the triplets data pipeline framework.

Cloudflare Workers AI provider for anyllm using the workers-rs binding

Reusable OpenAI-compatible transport and normalization toolkit for anyllm providers

High-performance, local AI memory with AAAK v3.2 protocol and temporal Knowledge Graph

Deferred tool loading with ToolSearch and probability-based deferral for Awaken

Multi-protocol HTTP server with SSE, mailbox, and protocol adapters for Awaken

Rule-based context message injection plugin for Awaken

A flexible, multi-backend, customizable AI agent framework, entirely based on Rust.

Core types, traits, and algorithms for the triplets data pipeline framework.