Reading the repo — stats and the shipped feed land in about ten seconds…
Framework to build resilient language agents as graphs.
3.3k 600 196 openLast shipped 35m ago
Framework to build resilient language agents as graphs.
The week focused on stability improvements in the SDK, addressing issues with stream handling, error retry logic, and state synchronization. Key fixes included proper HTTP status preservation on protocol errors, preventing unnecessary 4xx retries, reconciling stream buffers after run cancellations,…
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 langgraphjs'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(langgraph): don't walk history for a DeltaChannel that was never written (#2927)
fix(langgraph-checkpoint-postgres): anchor namespace matching to segments (#2825)
fix(langgraph-checkpoint-redis): match namespaces at segment boundaries (#2829)
fix(sdk): URL-encode identifiers in request paths to prevent endpoint redirection (#2944)
fix(langgraph-checkpoint-mongodb): re-check namespace in MongoDBStore vector search (#2931)
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.
