Reading the repo — stats and the shipped feed land in about ten seconds…
⚙️🦀 Build modular and scalable LLM Applications in Rust
8.8k 986 113 openLast shipped 30m ago
⚙️🦀 Build modular and scalable LLM Applications in Rust
Rig shipped item-shaped assistant history with provenance tracking, added Gemini 3.8 Flash and DeepSeek Flash model constants, and introduced new APIs like non-panicking cassette operations and unanswered transcript support. The bulk of the week focused on substantial internal cleanup: unifying…
Get this in your inbox every Monday →A deterministic 0–100 hygiene score — README, license, CI, tests, docs, and freshness.
Who ships this repo — author concentration and the bus factor across the last 300 mainline commits.
How welcoming this repo is to contributors — issue throughput, close time, responsiveness, and good-first-issue count.
What this project is built on — dependency count by ecosystem, the license mix, and anything worth a legal look before you adopt it.
Whether this project's CI can be trusted — pass rate, run times, flaky runs, and which workflow is the weak link.
Grounded in rig's README, structure, and recent commits — answers won't invent code they haven't seen.
A Monday email with what shipped, in plain English — no account needed.
Showing raw commit titles for the newest commits. Sign in to generate AI summaries.
fix(rig-agent)!: RunSpec carries accept_unknown_finish_reasons; one clearable malformed-call limit; RunSpec::default matches new (#2733)
refactor!: non-exhaustive enums that are expected to grow (#2735)
refactor(core)!: one name for the unknown-finish-reason setting (#2734)
fix(anthropic): Xiaomi MiMo's Messages preset no longer posts to /v1/v1/messages (#2738)
fix(gemini): record streamed response id and model once, not per chunk (#2732)
feat(ollama)!: native `/api/chat` route with `options`, `num_ctx`, `keep_alive`, `think` and the inline `<think>` split (#2730)
feat(cohere)!: native documents, citations and tool_plan (#2729)
feat(rig-agent)!: offer malformed tool arguments to the invalid-call hook and bound their retries (#2727)
fix(telemetry): record streaming as gen_ai.request.stream, not an operation (#2724)
fix!: unknown finish reasons are one outcome, a caller's choice, and never silent (#2726)
A floor, not a guess: counts only commits whose author, co-author trailer, or message explicitly credits an AI tool (Claude, Copilot, Cursor, aider, Codex…). Based on 30 mainline commits. Unattributed AI code isn't counted here — the full audit estimates that separately.
