Sourcegraph

Today, we're announcing Sourcegraph 7.0, a release that marks the beginning of a new chapter for our company and product. Over the past several releases, we've shifted our focus. We're doubling down on being the intelligence layer that developers and AI agents rely on to navigate, understand, and operate on large codebases. sourcegraph.com/blog/a-new-era…

NEW: lessons learned on how to make a REALLY great enterprise @SlackHQ bot for AI products from our experience @Sourcegraph Touches on interactive and real-time feedback (critical when agents are doing asynchronous work), summaries and previews for the Slack UI, rate limiting, and more. Thanks @juliaxu_xu__ @JasonHawkHarris & Emi for spreading the knowledge sourcegraph.com/blog/deep-sear…

@shrikant__j @DanielNealAdler Deep-ish dive =) sourcegraph.com/blog/building-…

@DanielNealAdler @Sourcegraph Yes would like to know more about the custom harness and tracing the agent lifecycle.

We've shifted a ton of our operations work at @Sourcegraph to agents via slack bots. All self-hosted, consistent across all users, with carefully curated tools from our systems. Would a deep how-to on this be useful? DataBot, IncidentBot, CloudTriageBot, InstanceConfigBot, etc, etc (I'm sure these custom harnesses will be bitter-lessoned someday, but incredibly useful today.)

@sgjarmak @qdrant_engine @mlopscommunity humans🤝agents

Had a great time speaking at the @qdrant_engine x @mlopscommunity event last night. TL;DR: scientific knowledge is fragmented and weakly linked. If we surface those connections (like we do across codebases at @Sourcegraph), both humans and agents navigate better. Built a prototype on @SciXCommunity data: postgres + pgvector, semantic community clustering, NER pipelines, graph context, structural parsing -> MCP agent tooling. The ultimate goal of this work is to surface more scientific connections to reduce our collective “scientific tech debt” and accelerate discovery. Slides + demo: lnkd.in/eRx9fum7

You can now use search contexts in Deep Search to ask questions within a set of repositories.

@taiyab :chefs-kiss:

We've just launched a new homepage ✨ sourcegraph.com

Deep Search can now search Git tags, ancestry, and commits on any branch to pinpoint where a change lives in your Git history.

We just launched Smart Hover Summaries in beta. It reads your code to give you quick access to show key architectural details on hover.

More ways engineering teams manage and transform large codebases: sourcegraph.com/use-cases?&utm…

Code coverage numbers do not mean much if parts of your pipeline are being skipped.

I'm giving a talk at a @mlopscommunity + @qdrant_engine workshop in a couple weeks in Boston on structuring scientific knowledge for agent-driven discovery :) Workshop link: luma.com/19c49kvs

@webuyhomecash graph

Comment "graph" and I'll send you the link. Graphify turns your entire codebase into a visual knowledge graph — code, docs, even video and audio. Free, open-source replacement for Sourcegraph and CodeScene. #github #opensource #developer

@remondimi @ryan0x44 @sqs @AmpCode Excellent points.

@ryan0x44 @sqs @AmpCode Makes sense tbh. @Sourcegraph has been working hard on semantic understanding of code for years and all of that tooling and plugging into the code at a lower level provides a significantly better harness for the agent

I still don't get how @AmpCode smart mode (which uses Opus 4.6 under the hood) can have so much better taste than Claude Code using Opus 4.6, the difference is massive. I mean I understand how, but it's hard to believe it's this big of a difference.

We fine-tuned a small model to convert natural language into Sourcegraph search queries in under 400 ms. Skip the DSL, just describe what you need.

View everything else shipped: sourcegraph.com/changelog/2026…

4/4) Batch Changes for Bitbucket supports OAuth sourcegraph.com/changelog/batc…

What's new in Sourcegraph, and no, we're not fooling around. 1/4) Query assist: search code in natural language