143.dev
we open-sourced our internal coding-agent infrastructure
Details
- External ID
- 48736251
- Source
- HN
- Company
- —
- Product
- —
- Website domain
- —
- Launched
- June 30, 2026
- Cohort
- —
- Upvotes
- 13
- Upvotes percentile
- 0.6707650273224044
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
We just open-sourced the internal system we built at Assembled for running coding agents as a team.Coding agents worked well for individual engineers, but the surrounding workflow was a bit of a mess. We generally found that many engineers had different MCP connections and context for their agents, personal automations running that other people couldn’t access, and very little introspection for what a human’s input into the coding agent looked like.So we built an internal system that converted coding agents into shared team infrastructure.The system runs Codex, Claude Code, OpenCode, and other agent harnesses in gVisor sandboxes. You can mix and match coding agents to tune your cost and intelligence tradeoff (for example, our team has started to use GLM 5.2 for automation tasks and a combination of Codex/Claude Code for manual tasks). It connects to a bunch of tools like GitHub, Linear, Sentry, Slack, PagerDuty and makes previews easy to generate.We were inspired by internal systems like Stripe Minions and Ramp Inspect, but wanted an open version other teams could inspect, run, and adapt so we made it MIT-licensed and self-hostable.Hope you like it!Website: https://143.devGithub: https://github.com/assembledhq/143
Enrichment
- Theme
- developer tools for AI agents
- Vertical
- Horizontal
- Function
- Agent / copilot
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- open-source coding agent infrastructure
- Manually corrected
- False
Could you build this?
Partial Wrapping MCP servers and orchestrating coding agents for a team can start with basic templates, but managing secure shared remote environments, state synchronization, and reliable tool orchestration across multi-developer teams requires specialized DevOps and infrastructure plumbing.
What it would actually take: Requires an orchestration backend (Node.js/Go) connected to container runtimes (like Docker or Firecracker microVMs) to execute agent actions securely in isolated sandboxes. The hard parts are maintaining synchronized context/MCP configs across engineers, handling distributed filesystem diffs, and orchestrating secure, authenticated agent callbacks without leaking developer environment credentials.
Discussion
3 comments analyzed.
Competitors mentioned: speech-core
Feature requests: Voice capabilities (Linux, Windows, Android), Multiple changesets in single session, Memory across runs
Competitors
Other products that read as similar to this one — 771 launches clear the similarity bar, closest 8 shown.
Attention rank: #285 of 772 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 240 days after the earliest competitor.
- Mistle · hn · 2026-05-13 · 6 upvotes · similarity 0.54
- Mini-coder · hn · 2026-03-02 · 6 upvotes · similarity 0.53
- Sourceweave · ph · 2026-09-21 · 1 upvotes · similarity 0.53
- Runtime · ph · 2026-05-20 · 304 upvotes · similarity 0.52
- I built an open source multi-agent harness in Go · hn · 2026-04-08 · 6 upvotes · similarity 0.52
- Coding Agent Survey · hn · 2026-07-01 · 5 upvotes · similarity 0.51
- AgentBox · ph · 2026-09-25 · 1 upvotes · similarity 0.50
- 20+ Claude Code agents coordinating on real work (open source) · hn · 2026-02-12 · 53 upvotes · similarity 0.50
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.