Skip to content
@neul-labs

Neul Labs

High-performance infrastructure for AI agents.

Neul Labs

High-performance infrastructure for AI agents.

We build the fast parts of the AI stack. Rust-accelerated drop-in replacements for the tools agents actually depend on — LLM gateways, workflow engines, package managers, and developer tooling. Zero config. No rewrites. Just faster.

Website · Docs · Support

29 public projects · MIT/Apache 2.0


Flagship

🌟 Regulus — The EU & UK compliance plane for Google ADK. Runtime BasePlugin suite encoding 10 regulations (EU AI Act, GDPR, DORA, NIS2, EHDS, UK GDPR, FCA SYSC, PRA SS1/23, PRA SS2/21, NHS DSPT) and 6 governance frameworks as runtime profiles. Hash-chained audit envelopes, PII redaction, dual-control kill switch, fail-closed data residency. Java 21 · Maven · regulus-ai-adk-plugins · Repo


🦀 Rust-accelerated drops-ins for Python stacks

The agent stack is built on Python libraries that were never designed for production concurrency. We profile, rewrite the hot path in Rust, ship as a drop-in replacement. Your code doesn't change — it just gets faster.

Project What it accelerates Speedup (per the project)
fast-litellm LiteLLM connection pooling, rate limiting 3.2× pool, 2.8× rate limit
fast-langgraph LangGraph checkpoint + state management 700× checkpoint, 10–50× state
fast-crewai CrewAI serialization, tools, DB search 34× / 17× / 11×
fast-axolotl Axolotl LLM fine-tuning (dedup SHA256) Multi-threaded, no OOM
fastworker Python background workers No Redis. No RabbitMQ.
ormai Agent DB access (LangGraph / PydanticAI / SQLAlchemy / Tortoise) Safe text-to-SQL
fastagentic Production runtime for PydanticAI / LangGraph / CrewAI / LangChain Cached run_id, MCP server

🤖 Agent infrastructure

Project Description
mcp-pay Payment awareness layer for MCP (Model Context Protocol).
agentvfs Workspace runtime and execution boundary for AI agents.
brat Multi-agent harness for AI coding tools. Crash-safe state, parallel execution, one CLI.
ringlet One CLI to rule all your coding agents. Profile-isolated, cost-tracked.
grite The issue tracker that lives in your repo. Built for AI agents.
memorg Give your LLM a memory that actually works.
stratafs A semantic filesystem that turns file storage into a searchable knowledge base.
openclawOS OS-like architecture for AI assistants with kernel-based, process-isolated applications.
openclawMU Multi-tenant fork of OpenClaw with strict data isolation.
openclaw-rs Community Rust implementation of OpenClaw.
ukkin Create AI agents on your phone that automate your daily tasks.
m9m The n8n alternative without the bugs — faster, more reliable workflow automation in Go.

🛠️ Developer tools (Rust rewrites of CLI classics)

Project Description
gity Make large Git repositories feel instant.
stout Stout is a drop-in replacement for the Homebrew CLI that's 10–100× faster for most operations.
stout-index Pre-computed package index for stout.
rjest A blazing-fast Jest-compatible test runner. 100× faster warm runs. Zero config changes.
rpytest Run your pytest suite faster. Change nothing.
rninja Build faster. Cache smarter. Drop-in ready (Ninja replacement).
recurl curl that just works. Drop-in replacement with automatic anti-bot bypass.
rewget wget, but it works everywhere.
stkd Stacked Diffs for GitHub and GitLab (Graphite-compatible).

Why we exist

The AI agent stack is built on Python libraries that were never designed for production concurrency. LiteLLM's connection pool uses stdlib locks. LangGraph checkpoints serialize through a single thread. Package managers shell out to Ruby. The result: agents that work great in a demo and fall over in production.

We fix these bottlenecks one at a time: profile, rewrite the hot path in Rust, ship as a drop-in replacement. Your code doesn't change. It just gets faster.

Contributing

Every project is MIT or Apache 2.0 licensed and accepts contributions. See the individual repository for setup instructions.

Contact

support@neullabs.com · neullabs.com · docs.neullabs.com

Pinned Loading

  1. fast-litellm fast-litellm Public

    High-performance Rust acceleration for LiteLLM - providing significant performance improvements for connection pooling, rate limiting, and memory-intensive workloads.

    Python 45 4

  2. fast-langgraph fast-langgraph Public

    High-performance Rust accelerators for LangGraph applications. Drop-in components that provide up to 700x speedups for checkpoint operations and 10-50x speedups for state management.

    Python 21

  3. m9m m9m Public

    The n8n alternative without the bugs — faster, more reliable workflow automation.

    Go 3

  4. grite grite Public

    The issue tracker that lives in your repo. Built for AI agents. Works for humans.

    Rust 6 1

  5. brat brat Public

    Multi-agent harness for AI coding tools. Crash-safe state, parallel execution, one CLI.

    Rust 3

  6. ringlet ringlet Public

    One CLI to rule all your coding agents.

    Rust 3 1

Repositories

Showing 10 of 33 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…