Hive

Active Rust Tokio PostgreSQL WASM Axum

Hive is a self-hosted agent harness written in Rust. It manages long-lived agents as durable processes, connects them to external communication channels, and enforces security boundaries between agents, data, and the outside world using kernel-level primitives rather than application-level trust.

The core systems are functional and I'm using Hive daily for my own workflows. I plan to open-source it once the codebase is in a state I'm comfortable with.

Agents run in isolated environments with overlay filesystems, scoped capabilities, and per-process network filtering enforced through eBPF. A structured knowledge graph built on typed ontologies handles reasoning. A shared ticketing system coordinates work between agents and humans across sessions. Browser automation runs through a headless Firefox instance behind a filtering proxy.

The architecture reference covers the major components and how they connect. The security model documents the enforcement layers in detail.

The Postgres Migration

2026-04-24 Sam Stelfox 8 min read

Another big structural for Hive. 723 files changed, 90,471 insertions, 132,463 deletions against upstream main at the fork point. SQLite is gone. PostgreSQL with pgvector is the only storage backend now. No migration path as this still isn't a real code base. The previous setup had Arc<Mutex<Connection>> contention, spawn_blocking wrappers everywhere because rusqlite isn't async, and client-side cosine similarity computation that should have been happening in the database all along.

Looking for something specific?

Log Entries

Ref Pages

6,750

Words

Code Blocks

20d

Build Span

0h 35m

Time to Read

2026-04-24 The Postgres Migration hive project rust security architecture
2026-04-08 API Security Hardening hive project security rust api authentication
2026-04-08 A Third Fork hive project ai agents open-source community
2026-04-04 Why Build Another Agent Harness hive project ai agents rust philosophy