Code Finder, a fast and efficient agent optimized specifically for code search, is now available in Beta through the Sourcegraph MCP server.

Code Finder is a tool that helps coding agents quickly locate relevant implementations, configuration, tests, or documentation within a single repository. It returns a concise summary with links and line ranges, giving your agent focused results it can immediately use.

Following its Beta period, the redesigned compare page is now generally available. It's a ground-up rebuild of how you view changes between two revisions — fast, complete, and built to stay useful even on very large diffs.

In the Agentic Batch Changes Beta, steps utilizing inner loop coding agents like Claude Code and Codex now stream thinking and progress in real time.

If you haven't heard already, Agentic Batch Changes is now available in Beta. This is a completely re-imagined way to apply code change at scale.

We're releasing a slew of new improvements to the Beta experience this week.

Codebases are growing and changing faster than ever, but the problem of maintaining systems - old and new - is not going away for codebase owners. If anything, it is becoming more important than ever. Today, we're taking the next step to meet this new era of software development with Agentic Batch Changes, available now in Beta: the frontier agent for code change at scale, built on technology designed for the world's largest codebases.

We are removing the need to manually manage your context window limits!

Compaction runs in the background, so there is nothing new to configure or learn. Keep asking follow-up questions, and Deep Search will make room when older conversation history starts to crowd the context window.

Deep Search can now use a dedicated subagent specialized for finding files relevant to your query in case a specific code domain needs to be researched. This subagent performs scoped searches and presents a summary to the main agent. Since the main Deep Search agent only needs to read this summary, this saves tokens in its context window.

This means Deep Search can explore more of your codebase while using fewer tokens, so you get more focused context and longer conversation. We expect this feature will significantly alleviate issues with deep single-question research - for multi-question, we just shipped auto-compaction.

Deep Search conversation history now has a Shared with me tab. It lists conversations you opened from a shared Deep Search link, separate from conversations you created yourself.

From the shared list, you can reopen, export, fork, or remove a conversation from your shared history without deleting the owner's original conversation.

Administration on Sourcegraph has historically been an all-or-nothing decision: either a user was an administrator and could do everything, or they weren't and couldn't access any admin surface. We've replaced this with a set of fine-grained RBAC permissions that map onto distinct admin responsibilities. Now you can grant users exactly the access they need and nothing more.

Eight new permission namespaces are available in the role editor (Site admin → Users & auth → Roles), each grantable independently to any role.

We are introducing a new compare page for viewing changes between two revisions.

Deep Search has always been good at finding and explaining code. It can now also count, rank, and aggregate it without blowing up the context window.

A new sandboxed scripting tool lets the agent run programmatic aggregations across many searches in a single turn. Questions that don't fit into a single query, e.g. top-N rankings, cross-search joins, distributions across many files, can now be answered end-to-end, with every underlying search still cited so you can verify how the answer was assembled.