BUILDERS / OPEN SOURCE / AI-NATIVE

BRINGING IDEAS TO LIFE

We are builders. Small team. AI-native. Shipping open source from zero.

Bootstrapped. No VC. We create open source tools to solve real problems and selectively partner with teams building meaningful things.

See what we build Work with us

Bootstrapped AI-Native Open Source No VC

What We Do

Three pillars of how we operate

🌐

Build Open Source

We create tools and ship them in the open. From AI runtimes to deployment tools — if we need it, we build it and share it.

🤖

AI-Native Workflow

Small team, massive output. AI is core to everything we do — not a bolt-on feature but how we actually work every day.

🤝

Partner Selectively

Premium partnerships with teams building meaningful things. Not an agency. Not cheap. Selective and high-quality.

Things We've Built

Open source tools shipped by our team

AI agent runtime — one binary, any model, any domain

⭐ 91 muvon/octomind

Community registry of specialist AI agents

⭐ 3 muvon/octomind-tap

Semantic code search with MCP

⭐ 436 muvon/octocode

AI memory management with MCP

⭐ 9 muvon/octobrain

Filesystem MCP server for AI

⭐ 8 muvon/octofs

Unified AI provider library in Rust

⭐ 6 muvon/octolib

View all projects Explore on GitHub →

For Builders

Follow our journey. Read the blog. Use our open source tools. Learn how a small team ships with AI-native workflows.

For Teams

Need a builder's perspective? We selectively partner with teams that value quality and want proven execution on meaningful projects.

Latest from the Blog

Building in public. Sharing what we learn.

How to debug AI agents with Octomind observability — per-request cost reports, token breakdowns, the JSONL session log, RUST_LOG tracing, machine-readable jsonl output, and OctoHub proxy logging every upstream LLM request

Debugging AI Agents: The Observability We Wished We Had on Day One

An agent burned $4 and 90 tool calls on a task that should have taken three, and we were staring at a blank terminal. This is the instrumentation that turned guesswork into a two-minute diagnosis — Octomind's /info, /report, /context, the zstd session log, RUST_LOG tracing, --format jsonl, and OctoHub in front to capture every upstream request.

Late July 2026 release round-up for the Muvon AI stack — Octocode 0.19.0 reasoning retrieval and weighted RRF, Octobrain 0.9.4 async knowledge sync, Octolib 0.26.1 with Kimi K3 and Opus 5, Vext 1.3.0 glass design system with word-level speaker splitting and seven languages

Release Round, Late July 2026: Octocode 0.19.0, Octobrain 0.9.4, Octolib 0.26.1, Vext 1.3.0

Two and a half weeks since the July round, and the stack learned to check its own work. Octocode 0.19.0 shipped reasoning retrieval — an LLM re-ranker fused into hybrid search with weighted RRF, +36% MRR on the benchmark. Octobrain made knowledge sync non-blocking, Octolib kept the model roster and embedding pricing current, and Vext 1.3.0 landed a glass redesign, word-level diarization, and two new languages.

Pairing Octocode semantic code search with Octobrain persistent memory so an AI agent can both find the right code and remember the decisions about it

A Map and a Memory: Pairing Code Search with Persistent Memory for AI Agents

Semantic code search lets an agent find the right code. Persistent memory lets it remember the decisions about that code. Run only one and you get an agent that re-derives context every session or remembers conclusions it can't relocate. Here is how to wire Octocode and Octobrain together so the agent both finds and remembers.

Let's Build Together

Have a meaningful project? We'd love to hear about it.