AI Agents (AGNT)
Sector · Show HN · data as of Oct 31, 2026, 3:03 PM UTC
launches · 7D Oct 24–Oct 30 vs Oct 17–Oct 23 (174)
hit rate · Oct 22–Oct 28 settled (9/182) vs Oct 15–Oct 21 (8/164)
— Not significant at current sample size: +0.1pp, z = 0.0 (needs |z| ≥ 2); 8/164 → 9/182.
trending score
Launches & hit rate
3 days left blank: votes still coming in (launches under 48h old), incomplete day, or no launches — not shown as zero.
Faded bars are incomplete days (today, or days before every selected source was being collected).
Key statistics
- Launches
- 26Oct 30
- Avg daily launches
- 26.027d
- 7D range
- 15 – 37Oct 24–Oct 30
- Hit rate
- 4.9%9/182 · Oct 22–Oct 28
- Volatility
- 51%26 daily chg
- Share of market
- 18.0%7D
- Top source
- Show HN100%
- Previous window
- 174Oct 17–Oct 23
Stocks in this sector (AGNT)
Launched on Oct 30 (the latest complete UTC day) or listed since the previous run (IPO), ranked by current traction. Product Hunt launches all list at 07:01 UTC; their traction has had at most one or two daily updates. 33 matches. Spam giveaways excluded.
| # | Sector | |||||||
|---|---|---|---|---|---|---|---|---|
| 1 | Sketch Stadium watch your agent play Pictionary | AGNT | 35 | +33 | — | 10 | 10 | 3d ago |
| 2 | Apache 2.0 Registry to let agents share skills with each other | AGNT | 9 | 0 | 0.0% | 1 | 5 | 3d ago |
| 3 | Ultrafast Rust Based Agent Workspace | AGNT | 7 | +7IPO | — | 19 | 19 | 2d ago |
| 4 | Agent-arcade Terminal games that pause when Claude Code/Codex is done | AGNT | 4 | +4IPO | — | 2 | 2 | 2d ago |
| 5 | Fastbrowse, Browser agent that picks clicks with a System One model | AGNT | 3 | +3IPO | — | 2 | 2 | 2d ago |
| 6 | Beolis Manage your coding AI agents | AGNT | 3 | 0 | — | 0 | 1 | 3d ago |
| 7 | SkillWire, a searchable catalog for coding-agent skills | AGNT | 3 | +3IPO | — | 0 | 0 | 2d ago |
| 8 | Tadpole an LLM agent built from scratch then post-trained on 4B model | AGNT | 3 | +3IPO | — | 0 | 0 | 2d ago |
| 9 | MCP for Your Mac Hardware | AGNT | 2 | +2IPO | — | 2 | 2 | 3d ago |
| 10 | Claude Code guards built from my agent's repeated mistakes | AGNT | 2 | 0 | — | 0 | 1 | 3d ago |
| 11 | mobile-agent Let AI agents control Android and iOS devices | AGNT | 2 | +2IPO | — | 0 | 0 | 2d ago |
| 12 | Imza plan and review focused coding agent | AGNT | 2 | +2IPO | — | 0 | 0 | 2d ago |
| 13 | Breatic Collaborative canvases and documents with an AI agent | AGNT | 2 | 0 | — | 0 | 0 | 3d ago |
| 14 | AI agents trade privately on BitcoinZ, with proof of delivery | AGNT | 2 | 0 | — | 0 | 0 | 3d ago |
| 15 | SpecDeck Bring coding agent decisions back into the spec | AGNT | 2 | 0 | — | 0 | 0 | 3d ago |
| 16 | Kitepod A free WordPress MCP with staging, approvals and undo | AGNT | 2 | +1 | — | 0 | 0 | 3d ago |
| 17 | Opencommerce OpenRouter for commerce, one API for AI agents to buy | AGNT | 1 | — | — | — | 1 | 3d ago |
| 18 | Korea-data-MCP Korean public APIs that agents can't misread | AGNT | 1 | 0 | — | 0 | 1 | 3d ago |
| 19 | AI agent needs process to build a commercial application | AGNT | 1 | 0 | — | 1 | 1 | 3d ago |
| 20 | Cc-pair Claude Code and Codex review each other's work | AGNT | 1 | — | — | — | 0 | 3d ago |
| 21 | I built a safety gate for autonomous coding agents | AGNT | 1 | +1IPO | — | 0 | 0 | 3d ago |
| 22 | CourtlyGo open database of tennis, pickleball, padel courts and MCP | AGNT | 1 | +1IPO | — | 0 | 0 | 3d ago |
| 23 | Governor, a firewall for AI agent spend and tool calls | AGNT | 1 | +1IPO | — | 0 | 0 | 2d ago |
| 24 | Archwhere work alongside AI coding agents on an architecture map | AGNT | 1 | +1IPO | — | 0 | 0 | 2d ago |
| 25 | InBox Wall A local-first, open-source email sanitizer for AI agents | AGNT | 1 | +1IPO | — | 0 | 0 | 2d ago |
| 26 | CodeConnect Coding Agents on Your iPhone | AGNT | 1 | +1IPO | — | 0 | 0 | 2d ago |
| 27 | HiveOS Multi-agent enterprise OS with PII pills and 3-model consensus | AGNT | 1 | 0 | — | 0 | 0 | 3d ago |
| 28 | Send21 Crypto pay links an AI agent can create but can't spend | AGNT | 1 | 0 | — | 0 | 0 | 3d ago |
| 29 | Navital Gym open environments for testing AI agents on Indian tasks | AGNT | 1 | 0 | — | 0 | 0 | 3d ago |
| 30 | Mydash a self-hosted inbox for what Claude Code and Codex produce | AGNT | 1 | 0 | — | 0 | 0 | 3d ago |
| 31 | Strim a Swift/MLX model server for coding agents on Apple Silicon | AGNT | 1 | 0 | — | 0 | 0 | 3d ago |
| 32 | Omneum Local, text-blind context control plane for AI agents | AGNT | 1 | 0 | — | 0 | 0 | 3d ago |
| 33 | Dbprint Database Context for Agents | AGNT | 1 | 0 | — | 0 | 0 | 3d ago |
Traction = current votes (PH) / points (HN) — early-adopter attention, not downloads or usage. Gained = traction gained between the two latest daily ingest runs; Gain % only when the previous traction was 5+. Buzz = comments gained in that interval. “frozen” = no longer tracked, so no current gain. How it works