Artificial Intelligence
hf-xet
1.7.0 GrowingClient library and tooling for the Hugging Face Xet data storage system.
xet-runtime
1.7.0 GrowingAsync runtime, configuration, logging, and utility infrastructure for the Hugging Face Xet client tools.
xet-data
1.7.0 GrowingData 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.
xet-client
1.7.0 GrowingClient library for communicating with Hugging Face Xet storage servers. Use through the hf-xet crate.
xet-core-structures
1.7.0 GrowingCore data structures including MerkleHash, metadata shards, and Xorb objects.
ai-agents
1.1.1 StableA Rust framework for building AI agents from YAML specifications with trait-based extensibility
bamboo-agent-core
2026.10.10 ExperimentalCore agent abstractions and execution primitives for the Bamboo agent framework
onde
1.3.2 GrowingOn-device inference engine for Apple silicon.
bamboo-sdk
2026.10.10 ExperimentalErgonomic top-level Agent SDK facade for the Bamboo agent framework
citadeldb-mem
2.7.0 ExperimentalEncrypted-first memory engine for AI agents, built on the Citadel database
liboxen
0.61.1 GrowingOxen is a fast data version control system, built with machine learning training data in mind. Designed to handle terabytes of data with ease, using a workflow similar to git. Version both structured and unstructured data of any modality: text, images, video, audio, CSV, Parquet, JSONL, model checkpoints, and more. liboxen is the embeddable core library behind the oxen CLI and server, which power fine tuning and inference pipelines for multimodal LLMs, image models, and video models on Oxen.ai.
ling-lang
2030.1.48 ExperimentalLing - The Omniglot Systems Language
lineprior
0.12.2 ExperimentalExplainable action ranking from historical sequences, with confidence, context backoff, evaluation, and tuning.
rpi-ai
0.3.17 ExperimentalUnified multi-provider LLM types + streaming, Rust port of pi-ai
memra-sampling
0.138.0 ExperimentalHost-side sampler chain (temperature/top-k/top-p/penalties, llama.cpp CPU sampler semantics) for the memra inference engine
memra-validate
0.138.0 ExperimentalNumeric validation helpers (reference comparisons, tolerance gates) for the memra inference engine
bamboo-agent
2026.10.10 GrowingA fully self-contained AI agent backend framework with built-in web services, multi-LLM provider support, and comprehensive tool execution
muthr
0.1.65 ExperimentalRuntime management CLI.
rpi-agent
0.3.17 ExperimentalAgent runtime + loop, Rust port of pi-agent-core core layer
memra-kv
0.138.0 ExperimentalKV-cache format policy (q8_0/q5_1/q4_0/fp8 block layouts) for the memra inference engine
memra-gguf
0.138.0 ExperimentalGGUF and HF-safetensors model loading, quant-format decode, and tensor inventory for the memra inference engine
memra-tokenizer
0.138.0 ExperimentalGGUF-native BPE/SPM tokenizer with chat-template support for the memra inference engine
memra-runtime
0.138.0 ExperimentalCUDA runtime scaffolding (context, GEMM checks) for the memra inference engine
memra-lanes
0.138.0 ExperimentalServing-lane types, SLO admission policy, and engine-truth step stats for the memra inference engine
pond-db
0.19.5 ExperimentalLossless storage and search for sessions from any AI agent client
causasv
0.8.9 ExperimentalCausal feature attribution via Asymmetric Shapley Values (ASV) over DAGs — Rust + Python
citadeldb-mcp
2.7.0 ExperimentalModel Context Protocol (MCP) server exposing Citadel encrypted memory as tools
citadeldb-ai
2.7.0 ExperimentalAutonomous agent runtime for Citadel: ReAct + Reflexion + memory-backed plan caching
molo-core
0.6.0 ExperimentalCore protocol types and traits for molo
rpi-tools
0.3.17 ExperimentalBuilt-in agent tools (read/write/edit/bash/grep/find/ls) + ExecutionEnv, Rust port of pi harness tools
symbiont-macros
0.43.0 ExperimentalProc macros for symbiont hot-reloadable function declarations.
memra-reference
0.138.0 ExperimentalPortable unfused ModelPlan reference executor for memra correctness gates
mcp-session
0.2.0 ExperimentalBounded session management for MCP servers — max sessions, FIFO eviction, rate limiting
prism-ann
0.3.1 ExperimentalFiltered approximate nearest-neighbor vector search
awaken-agent
0.6.0 ExperimentalCompatibility umbrella crate re-exporting awaken
rullama-finetune
0.12.0 ExperimentalCloud fine-tune APIs (OpenAI, Anthropic, Together, Fireworks, Anyscale, Bedrock, Vertex AI) for the rullama agent framework. Dataset pipelines live in `rullama-datasets`; local LoRA/QLoRA/DoRA fine-tuning lives in `rullama-lora`.
relayrl_algorithms
0.6.0 ExperimentalIndependent / Multi-Agent Proximal Policy Optimization (PPO) Algorithms for the RelayRL framework
trusty-embedderd
0.4.1 ExperimentalUnified ONNX embedding daemon with stdio + Unix-socket transports and BatchQueue (issue #164).
zuoer
0.3.2 ExperimentalDomain-neutral run segmenter: the Silero-derived hysteresis state machine that turns any frame-probability sequence into contiguous runs with mean/peak aggregates — one instance per class for sound-event detection. Over it sits a backend-agnostic voice-activity-detection (VAD) shell: the VadBackend seam and the Speech* names. The model, inference runtime, and audio I/O live in the backend crate.
rigspark-core
3.0.2 ExperimentalDeterministic, offline LLM memory and VRAM sizing, KV-cache estimation, hardware-fit scoring and model catalog for rigspark.
thread
0.1.0 GrowingA safe, fast, flexible code analysis and parsing library built in Rust. High-level entry point for the Thread ecosystem.
elicitation
0.11.1 ExperimentalConversational elicitation of strongly-typed Rust values via MCP
molo-agent
0.6.0 ExperimentalAgent runtime, memory, channels, and tool registry for molo
cf-gears-mini-chat-sdk
0.10.26 ExperimentalSDK for mini-chat: policy plugin traits, models, and errors
lix-storage-rocksdb
0.19.0 ExperimentalEmbeddable version control for apps and AI agents.
rpi-harness
0.3.17 ExperimentalSession tree + JSONL persistence + compaction + AgentHarness loop, Rust port of pi harness layer
anno
0.13.0 ExperimentalNER, coreference resolution, relation extraction, PII detection, and zero-shot entity types
decapod
0.106.1 ExperimentalDecapod is a Rust-built governance runtime for AI agents: repo-native state, enforced workflow, proof gates, safe coordination.
flodl
0.8.0 ExperimentalfloDl — a flow-graph deep learning framework built on libtorch
molo-macros
0.6.0 ExperimentalProcedural macros for molo: one-shot tool definitions (#[molo::tool])