Ollama
Ollama becomes a gateway provider for Claude Desktop — and this feed missed the release that says so.
A side-by-side editorial comparison of GitHub Copilot and Sourcegraph — release velocity, themes, recent moves, and the top alternatives to consider.
The Agents window now opens without a GitHub sign-in, if you bring an Anthropic key.
August's VS Code releases (v1.132 through v1.135) concentrated on the Agents window: chats arranged side by side, a /btw side conversation that shares the parent chat's context and prompt cache, a prompt timeline for navigating long transcripts, and Agent Host connecting one session across multiple windows. The notable items are the ones that loosen GitHub's grip on its own surface — an experimental setting opens the Agents window without a GitHub sign-in when Claude is configured with an API key, model providers can be switched between Anthropic and Copilot subscriptions mid-session, and sessions started in other applications can be listed and continued in VS Code. Plugins following the Agent Plugins 1.0 standard install across VS Code and other compatible clients.
Sourcegraph stopped selling search to developers and started selling retrieval to their agents.
The product line has reorganized around coding agents as the customer. Code Finder runs its own search loop and hands an agent exact files and line ranges; Deep Search now executes scripts in a sandbox against the search APIs so a migration audit returns a CSV checklist rather than thousands of files of tokens; Agentic Batch Changes entered public beta to scope and ship migrations across hundreds of repositories. The argument threaded through all of it is that an agent searching on its own is slower, costlier, and worse than one handed scoped results.
August's VS Code releases (v1.132 through v1.135) concentrated on the Agents window: chats arranged side by side, a /btw side conversation that shares the parent chat's context and prompt cache, a prompt timeline for navigating long transcripts, and Agent Host connecting one session across multiple windows. The notable items are the ones that loosen GitHub's grip on its own surface — an experimental setting opens the Agents window without a GitHub sign-in when Claude is configured with an API key, model providers can be switched between Anthropic and Copilot subscriptions mid-session, and sessions started in other applications can be listed and continued in VS Code. Plugins following the Agent Plugins 1.0 standard install across VS Code and other compatible clients.
Copilot is increasingly a host rather than a destination. The portable plugin standard, the cross-application session list, and the provider switcher all treat the model and the customizations as things the user brings, which is consistent with GitHub publishing Agent Plugins 1.0 as a shared spec rather than a proprietary format. The counterweight is administrative: policy and billing changes were pre-announced this month and a global model policy reached general availability, so the client layer opens while control consolidates in enterprise settings.
Expect the sign-in-free Agents window and the /rubber-duck second-opinion command to graduate out of experimental, and enterprise policy to gain per-provider controls now that non-Copilot subscriptions can drive sessions.
The product line has reorganized around coding agents as the customer. Code Finder runs its own search loop and hands an agent exact files and line ranges; Deep Search now executes scripts in a sandbox against the search APIs so a migration audit returns a CSV checklist rather than thousands of files of tokens; Agentic Batch Changes entered public beta to scope and ship migrations across hundreds of repositories. The argument threaded through all of it is that an agent searching on its own is slower, costlier, and worse than one handed scoped results.
Two consequences of that repositioning are already showing. First, Sourcegraph is pushing into other vendors' agents rather than waiting for its own surface — reranking Claude Code's file picker on symbols instead of path characters is integration work on someone else's tool. Second, scoped retrieval is being sold as governance: if you can prove which files an agent read before it shipped a change, agent context becomes an audit trail, which is the wedge into regulated engineering teams. The security posts extend the same logic from migrations to vulnerability remediation across ten thousand repositories.
Expect Agentic Batch Changes to move from public beta toward general availability, and more retrieval integrations into third-party coding agents. The provenance angle looks like the basis of an enterprise tier aimed at regulated buyers.
Other ai-assistants products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either GitHub Copilot or Sourcegraph.
Ollama becomes a gateway provider for Claude Desktop — and this feed missed the release that says so.
Gemini stops watching video frame by frame and starts deciding what to watch.
Qodo is arguing that AI code review needs governance, not better instruction files
D-ID's feed is a content-marketing engine, not a changelog
Pictory publishes daily search content, not a changelog.
The OSS terms change takes effect today, under a steady drumbeat of agent-memory explainers.
See all GitHub Copilot alternatives → · See all Sourcegraph alternatives →
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
They serve adjacent needs but don't currently overlap on shipped themes. GitHub Copilot is currently shipping more aggressively (velocity 10.0 vs 5.0), with 0 editorial sparks in the last 30 days against 0. See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. GitHub Copilot is currently shipping more aggressively (velocity 10.0 vs 5.0), with 0 editorial sparks in the last 30 days against 0. For your specific use case, the alternatives sections above list other ai-assistants products to evaluate alongside.
Top GitHub Copilot alternatives in ai-assistants are ranked by recent ship velocity. Browse the "GitHub Copilot alternatives" section above for the current picks, or visit /alternatives/github-copilot for the full list with editorial commentary on each.
Top Sourcegraph alternatives in ai-assistants are ranked by recent ship velocity. Browse the "Sourcegraph alternatives" section above for the current picks, or visit /alternatives/sourcegraph for the full list with editorial commentary on each.