Show HN: An inbox for your AI coding agents (herdr plugin)
The herdr-agent-inbox plugin adds an inbox‑style interface for managing AI coding agents within the herdr environment. It provides session titles, triage queues, running‑time displays, workspace rollups, and resumable chat history for agents such as Claude, Pi, and Codex. Installation requires herdr ≥ 0.7.0 and Python 3.11+, and the plugin is configured via standard herdr plugin settings.
- ▪The plugin creates a sidebar inbox where agents are organized by state such as blocked, working, idle, and settled.
- ▪Session titles are generated from each agent's conversation and can be summarized by a configurable LLM command.
- ▪Users can settle, mark unread, or regenerate titles through defined keybindings like prefix+m and prefix+shift+m.
- ▪Closed chats are retained in a global history browser and can be resumed with commands like claude --resume.
- ▪Configuration files and keybindings are managed through herdr’s TOML config and hot‑reloaded on changes.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,266 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/douglascorrea/herdr-agent-inbox |
| Publication time | Thu, 23 Jul 2026 19:54:00 +0000 |
| Retrieval time | 2026-07-23T20:11:52.789Z |
| Last seen | 2026-07-23T20:11:52.789Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | zQsvVAQhin8z · 2 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
herdr-agent-inbox An inbox for your coding agents. Session titles, settle / mark-unread triage, running times, workspace rollups, and a ChatGPT-style resumable chat history — for every agent running in herdr. Inspired by T3 Code's "settle" workflow: "Think of it more like an inbox. When you're done with a thread, click the 'settle' button and it slides to the bottom. This has helped me 'finish' more." What you get Session titles — every agent pane gets a real title derived from its conversation ("Fix flaky payment webhook tests"), not just claude or a directory name. Reads the agent's native transcript (claude / pi / codex), optionally summarized by any LLM command you configure.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.