Radar / AI infrastructure / Atuin Threads
Atuin Threads: all your coding-agent sessions, searchable and synced across machines
Atuin 18.24 adds Threads, a searchable, end-to-end-encrypted history for coding-agent sessions that follows a developer across laptops, servers and ephemeral boxes — and lets a session resume in a different agent harness.
Why it matters
Solves the scattered-context problem of the multi-agent era: start a task in Claude Code on one machine, resume it in Codex on another with context intact.
What you could build with it
A developer juggling several machines could use Threads to keep every agent session searchable and resumable, so an abandoned debugging attempt from a laptop can be picked up on a dev server — or forked into a different coding agent — instead of starting over.
Does it hold up?
Shipped and working in Atuin 18.24+ across five agent harnesses, with opt-in capture and encrypted sync or fully local use. The HN thread's main caveat is security: indexed transcripts can hold leaked credentials, so teams should weigh that before syncing sessions.
Built with Atuin Threads
- Atuin Threads syncs AI agent sessions across machinesHyveNews · HN-linked report on the Nov 11 Hacker News thread (~200 points): Threads tracks and syncs agent sessions across devices for distributed agent work.
- Atuin Threads launches: all your agent sessions on every machineAGI Hunt · Launch summary: unified history and retrieval over scattered session logs for developers running multiple coding agents across devices.
- G:HN digest — Atuin 18.24 introduces ThreadsHN digest · HN discussion digest: supports Claude Code, Codex, Pi, Omp and OpenCode; MCP integration lets agents search past sessions themselves; one commenter flagged credential-leak risks from indexing transcripts.
- atuinsh/atuingithub · 32,314 ★ · Atuin itself — open-source shell-history tool; Threads ships in Atuin 18.24+ with opt-in session capture and self-hostable sync.
Learn more
First spotted on article: source.
More AI infrastructure
vLLM v0.34.0: extensible KV cache by default, Model Runner V2 only, and 10 new modelsThe open inference engine's latest release spans 1,061 commits from 412 contributors, adds 10 models including Mistral…infra · JEV 0.86llama.cpp v1.0.0: the local-AI engine's first stable releasellama.cpp and ggml hit v1.0.0, promising semantic versioning so breaking C API changes only arrive with major bumps.infra · JEV 0.84colibri: run 744B-parameter MoE models on consumer hardwarePure-C inference engine with zero dependencies that streams MoE experts from NVMe disk, keeping hot experts on GPU…infra · JEV 0.78claude-mem: persistent memory plugin that lets coding agents pick up where the last session left offPlugin that hooks five Claude Code lifecycle events, compresses session activity into a local SQLite + Chroma store…infra · JEV 0.74FreeToken: datacenter-scale MoE serving on desktop GPUsAn edge-native mixture-of-experts serving engine from UC Berkeley researchers that runs 290B+ parameter MoE models on…infra · JEV 0.74GBrain: Garry Tan's self-wiring memory layer for AI agentsY Combinator CEO Garry Tan's open-source, markdown-first knowledge layer that gives OpenClaw and Hermes agents…infra · JEV 0.71
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.