Show HN: Dora – a tiny LLM agent with only bash tool
Dora is a lightweight, modular LLM agent kernel written in Go that operates with a single loop and two core interfaces: Model and Tool. It is stateless, lacking built‑in memory, policy engine, or middleware, and can be installed via platform‑specific installer scripts that support self‑updates. The project provides detailed build instructions, requiring Go 1.25 or newer, and reads provider API keys from environment variables for supported models.
- ▪The core architecture of Dora consists of a minimal loop and two interfaces, allowing developers to plug in custom models and tools.
- ▪Installation scripts are available for macOS, Linux, and Windows, and include verification of release checksums and optional self‑update capability.
- ▪Builds can be generated with make commands, offering both debug and stripped release binaries, and the installer defaults to placing the binary in $HOME/.local/bin.
- ▪Supported providers such as OpenAI, DeepSeek, and Trust require their respective API keys to be set in environment variables, with default model selections provided for each.
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,388 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/lgxz/dora |
| Publication time | Tue, 11 Aug 2026 08:03:05 +0000 |
| Retrieval time | 2026-08-11T08:10:42.332Z |
| Last seen | 2026-08-11T08:10:42.332Z |
| 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 | c0hcm4N1Wjn2 · 1 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
dora dora is a tiny, modular LLM agent kernel for Go. Its core is one loop and two interfaces: Model and Tool. See docs/architecture.md for module boundaries, dependencies, interfaces, and runtime flows. model := newMyModel() weather := newWeatherTool() agent, err := dora.New(model, weather) if err != nil { log.Fatal(err) } result, err := agent.Run(ctx, []dora.Message{ {Role: dora.RoleUser, Content: "What's the weather?"}, }) if err != nil { log.Fatal(err) } fmt.Println(result.Content) The agent is stateless. Keep result.Messages and pass them to a later call to continue a conversation. Scope The kernel supports optional model streaming events while keeping its baseline Model interface synchronous.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.