Agentic Batch Changes is available today. Describe a change once. It runs across 10 or 10,000 repositories, adapts where they differ, and reacts when CI fails. Agentic Batch Changes uses outcome-based pricing. You pay per changeset merged into your codebase. If a pull request doesn't merge, you don't pay for it. Read more here: sourcegraph.com/blog/introdu…

Code Finder is now generally available. sourcegraph.com/changelog/co…

Starting December 7, federal agencies will have as little as three days to remediate vulnerabilities in the highest-risk class of flaws. That urgency extends beyond the federal government. Remediation windows are shrinking while enterprise codebases keep expanding. At codebase scale, critical gaps emerge between the tools security teams rely on, slowing teams down as the pressure to act increases. See where enterprise security programs break down and what closing the gaps looks like: sourcegraph.com/blog/vulnera…

For the fifth consecutive year we're on the Inc. 5000's list of fastest growing companies! "We’re honored to be recognized on the Inc. 5000 again,” said @DanielNealAdler, CEO of Sourcegraph. businesswire.com/news/home/2…

We traced 517,604 commits across 120 established open source repositories to see how quickly agents are being adopted, where their code lands, and whether it sticks.

A vulnerability discovered in one repository may exist across hundreds more. Prevention, detection, and response share a hidden dependency. When visibility breaks at repository boundaries, all three weaken together. AI-generated code and dependency sprawl are making those gaps harder to see and the consequences harder to contain. See what connects the three and why repository-level security leaves critical gaps across the codebase: sourcegraph.com/blog/detecti…

From the Changelog Introducing Code Finder Beta and Compare Page GA piped.video/watch?v=VR74iU4m…

Not all AI coding tools approach codebase context the same way. Some rely on prompts. Others use indexing, repositories, MCP servers, or long-context approaches. Our comparison breaks down five approaches to codebase context and the tradeoffs behind each so you can determine which is best suited for your team's needs. sourcegraph.com/resources/co…

1/2) Most AI coding agent failures aren't model failures. They're context failures. When an agent can't see across your repos, it has to guess. Wrong paths, missing dependencies, and confident nonsense.

What does it take to run coding agents reliably in enterprise codebases? Not just better models. Better context. Better workflows. Better systems around the agent. Running Coding Agents in Enterprise Codebases explores the patterns emerging among teams moving from AI experimentation to production adoption. Get the guide: sourcegraph.com/resources/eb…

1/ Changing code in one repo is easy. Rolling that same change across tens or hundreds of repos is a different problem entirely.

Today we're launching Agentic Batch Changes in public beta, and we're proud of how it's turning out. Mercari engineer Patrick Klitzke used Agentic Batch Changes during our experimental preview to scope and begin patching a GitHub Actions security vulnerability across their codebase. "I was able to fix it with one prompt on both the Help Center frontend and backend, then extended this to all repos in Mercari. I found around 80 potential repos affected." The thing that made this work wasn't speed. It was the agent's ability to reason about each repository individually. Mercari's repos have similar setups, but not the same setup. A scripted find-and-replace would have collapsed. The agent handled the variation per repo, reacted to CI, and pushed follow-up commits where needed. Canva has been in the preview too, using it to split Batch Changes by code ownership across a Bazel monorepo. This is a public beta. There are rough edges and we're honest about that. But the core capability is working in real customer environments and we're ready to put it in more hands. Available today for Sourcegraph Cloud customers. Free during the beta period. Self-hosted arrives July 8 with Sourcegraph 7.5. Full announcement: sourcegraph.com/agentic-batc…

Heading to AI Engineer World's Fair? Visit Sourcegraph to learn how engineering teams are modernizing large codebases, managing AI-generated change, and building the foundation for reliable coding agents at enterprise scale. Stop by the booth, catch our sessions, and join us after hours. Learn more and schedule time with the team: sourcegraph.com/events/ai-en…

(2/2) sourcegraph.com/changelog/de…

Deep Search will now automatically compact long conversations when a follow-up question is close to the context window limit. (1/2)

From our changelog: - Auto-compaction for longer, uninterrupted Deep Search convos - New "Finder" subagent for smarter, token-efficient file discovery - Smart hover summaries are now GA piped.video/watch?v=yJU01Y_L…

You can now have longer Deep Search conversations on Sourcegraph Cloud. We added automatic compaction to help keep your threads manageable as they grow.

Agent failures in large codebases are not random. Data from 1,281 agent runs across 40+ large open source repositories reveals five repeatable failure patterns that show up across coding agents. Each failure pattern points to a different infrastructure problem and a different fix. Read: Why coding agents fail in large codebases (and what to do about it) sourcegraph.com/blog/why-cod…

Pin the dependencies that matter most sourcegraph.com/blog/depende…

We automated our security workflow by connecting @Hacker0x01 webhooks to Sourcegraph Deep Search. The system validates and finds fixes for vulnerability reports before you even start work. This helps us address issues faster and removes the manual effort of triaging reports. sourcegraph.com/blog/automat…