Blog
Building in public. Sharing what we learn.
Give an AI Agent a Filesystem Without Giving It Your Whole Filesystem
A security-minded guide to sandboxing AI agent file access with a filesystem MCP server. How Octofs scopes a working root, stays gitignore-aware, enforces non-interactive shell, and removes whole categories of foot-gun that raw bash and rm hand an agent — plus the protections it does not have and how to configure around them.
Running One AI Agent Across Many Models: A Multi-Model Routing Guide for Octomind
One model for everything got expensive and rate-limited. Here is how we route requests between LLMs inside a single Octomind agent — cheap models for the grunt work, a frontier model for the call that matters — with the real config keys, the provider list, and a model-selection cheat sheet.
AI Agent Memory Without the Noise: Scoping and Forgetting with Octobrain
Give an AI agent persistent memory and it will memorize everything until recall drowns in its own notes. Here is how Octobrain's memory scopes, the four-tool MCP surface, and autonomous consolidation turned a noisy junk drawer back into a memory that actually answers — plus a practical setup guide.
Octocode 0.18.0: A Reproducible Retrieval Benchmark and GraphRAG File-Level Expansion
Octocode 0.18.0 ships a reproducible semantic code search benchmark — 127 curated queries with line-range ground truth, plus a Loc-Bench harness over 560 real GitHub issues — and adds GraphRAG file-level expansion that pulls structurally related files into search before reranking. Open source, local-first, Apache-2.0.
Octobrain 0.9.0: Knowledge Goes Multiplayer
Octobrain 0.9.0 turns the knowledge layer into something a whole team can share: git-backed knowledge boxes ship curated rules and docs in a repo, sync in the background, and stay scoped per project or org. Memory scopes get human-readable names instead of opaque hashes. And recall got sharper — RRF multi-query fusion makes query decomposition actually pay off, Supersedes edges let the current fact outrank the stale one, and new temporal filters answer "what did I decide last week." Here is what changed and how to upgrade.
How to Index a Large Codebase for Semantic Code Search Entirely Locally
A hands-on guide to pointing an AI agent at a huge monorepo when grep stops being enough. How Octocode chunks code with tree-sitter, runs local embeddings with no GPU and no cloud, fuses semantic and keyword search, and exposes it all over MCP — plus the gotchas that bit us.
Octocode 0.17.1: Local Embeddings with Ollama, vLLM, and Any OpenAI-Compatible Server
Octocode 0.17.1 indexes your code with a local embedding provider — point it at any OpenAI-compatible server (Ollama, vLLM, LM Studio) and it auto-detects the model dimension, all on your own hardware.
Release Round, June 2026: Octocode 0.16.0, Octobrain 0.8.0, Octolib 0.23.0
Since our last release posts, the whole stack moved again. Octocode 0.16.0 turns one MCP server into a multi-repository server and adds Swift. Octobrain 0.8.0 goes zero-config — point it at a repo and memory binds itself. Underneath, Octolib 0.23.0 adds the shared git project-ID utilities, Claude Opus 4.8, and response schema enforcement.
Octobrain 0.7.0: Your AI's Memory Now Sleeps, Forgets, and Focuses
Octobrain 0.7.0 makes memory self-maintaining: autonomous sleep consolidation folds similar memories into clean insights, half-life decay lets unused ones fade, and goal-anchored consolidation collapses scattered notes around what you were actually trying to do. Plus HyDE recall on by default (+10-30% on vague queries) and a leaner 5-tool MCP surface. Here is what changed and how to upgrade.
TypeTab 1.0.0: On-Device Autocomplete for Your Whole Mac — Finish Every Sentence Before You Type It
We built TypeTab because typing is still the slowest part of using a computer. On-device autocomplete that finishes your sentences in every Mac app — Tab for the next word, Ctrl+E for the line. No cloud, no account, nothing leaves your Mac. $49 once — 50% off at launch.
Vext 1.2.0: Two-Pass Diarization, a Self-Healing Event Tap, and Five Languages
The engineering counterpart to the Vext 1.2.0 announcement. Why streaming diarization alone collapses fast back-and-forth, why we removed Apple's echo-cancellation API instead of fighting it, and how a global event tap can lie about being enabled after sleep.
Octocode 0.15.0: Local-First by Default, Hybrid Search Everywhere
Octocode 0.15.0 flips hybrid search and reranking on by default, ships a local model stack that needs zero API keys, and makes structural grep smarter about the patterns LLMs get wrong.