Caelis
Open-source runtime for long-running AI agent work
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
Caelis is an open-source, terminal-first runtime for long-running AI agent work. Run GPT-6 Astra as the lead agent and bring specialist models and ACP agents into the same local session. Participants exchange messages, use tools, and keep their own conversations. Follow their work in split panes, steer agents directly, and resume durable sessions with built-in memory and approval controls.
PH · launched Sep 18, 2026 · 1 upvote (top 69%) · 0 views
Niche: ai agent runtime environments · 858 launches, 611 in the last 7 days ▲ +1147% · Explore this niche →
Category and tags
- Horizontal
- Model & infra
- Developer
- AI-native
- Hobby / open-source project
- Open Source
- Developer Tools
- Artificial Intelligence
- GitHub
- OpenAI Day
Visit website ↗ Source listing ↗
More like this: all 858 launches in ai agent runtime environments →
Could you build this?
Partial A terminal-first runtime running multi-model agent protocols with native OS sandboxing (Seatbelt, Bubblewrap) requires lower-level systems and security engineering.
What it would actually take: The architecture requires a CLI daemon (written in Go, Rust, or Node) interfacing with low-level OS isolation primitives: macOS Seatbelt (sandbox-exec/libsandbox) and Linux Bubblewrap (namespaces, seccomp filters), paired with a multi-pane terminal emulator (like tmux integration or Ink/bubbletea). The hard part is managing cross-agent protocol message routing, secure subprocess sandboxing across multiple OS platforms, and lifecycle state persistence in an open-source terminal runtime.
Competitors
Other products that read as similar to this one : 1493 launches clear the similarity bar, closest 8 shown.
Attention rank: #1225 of 1494 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 319 days after the earliest competitor.
- Traccia · hn · 2026-11-09 · 5 upvotes · similarity 0.51
- Critiqor · ph · 2026-10-05 · 2 upvotes · similarity 0.46
- Cognis · ph · 2026-09-12 · 2 upvotes · similarity 0.46
- Scape · ph · 2026-10-13 · 84 upvotes · similarity 0.45
- Running AI agents across environments needs a proper solution · hn · 2026-03-24 · 8 upvotes · similarity 0.45
- Agyn, an open-source Kubernetes runtime for AI agents · hn · 2026-05-20 · 9 upvotes · similarity 0.45
- Agentic Orchestrator, a TUI for long-running coding agents · hn · 2026-06-30 · 20 upvotes · similarity 0.45
- kyora · github · 2026-10-04 · 29 upvotes · similarity 0.45
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.