Claude
Claude joins Google Meet calls as a participant that builds docs and slides live.
A side-by-side editorial comparison of Khoj and LobeChat — release velocity, themes, recent moves, and the top alternatives to consider.
Khoj gave its assistant long-term memory, then started winding down its own cloud.
The 2.0 beta line is doing two things at once. In February it gave Khoj long-term memories, moving the assistant from per-conversation context to knowledge that persists across sessions. Six weeks later it began deprecating Khoj cloud — a banner warning hosted users, and the subscribe option removed from the web app's settings page. The same release upgraded the web app to Next.js 15 and fixed the research agent stopping earlier than it should.
LobeHub v2.3.3 gives every agent an inbox, an address and its own reply rules.
LobeHub released v2.3.3 on November 12 with 253 merged PRs since v2.3.2. Agents and groups get IM-style direct Channels, each agent decides when to wake and reply, agents get a mail address and inbox whose runs report back to the owner, and projects can be created from a GitHub repository. On November 13 the CLI 0.0.84 let Channel agents message agents in other Channels, while the rest of the feed is desktop PR test builds.
The 2.0 beta line is doing two things at once. In February it gave Khoj long-term memories, moving the assistant from per-conversation context to knowledge that persists across sessions. Six weeks later it began deprecating Khoj cloud — a banner warning hosted users, and the subscribe option removed from the web app's settings page. The same release upgraded the web app to Next.js 15 and fixed the research agent stopping earlier than it should.
Khoj is consolidating around the self-hosted product and the model layer beneath it, and stepping back from running the hosted service. Model support has been broadening steadily — Gemini Pro 3, Minimax M2, Nano Banana image editing, configurable fallback models with admin-set priority — while Stability AI image generation was dropped. The client work follows the same logic: Obsidian batch sync, file query filter autocomplete, reference copying, all aimed at people running their own instance against their own files.
With subscriptions already disabled and a deprecation banner live, the next step for the hosted service is a shutdown date. The entries stop in late March 2026, so whether 2.0 has left beta since is not visible here.
LobeHub released v2.3.3 on November 12 with 253 merged PRs since v2.3.2. Agents and groups get IM-style direct Channels, each agent decides when to wake and reply, agents get a mail address and inbox whose runs report back to the owner, and projects can be created from a GitHub repository. On November 13 the CLI 0.0.84 let Channel agents message agents in other Channels, while the rest of the feed is desktop PR test builds.
LobeHub is turning from a chat client into a workspace where agents act like team members: tasks and MCP App views in v2.3.2, channels, identities and mail in v2.3.3. The canary already adds agent-run drive cleanup and in-thread replies, so the weekly cadence continues.
Expect v2.3.4 next week with more Channel behaviour, such as agents replying in threads, and projects tied to repositories; the canary lists both.
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 Khoj or LobeChat.
Claude joins Google Meet calls as a participant that builds docs and slides live.
Lambda adds IAM to its GPU cloud and plans a $33 billion Alabama data center.
Snorkel AI turns its coding benchmark on Fable 5.2 and finds the terminal failures mostly gone.
vLLM opens its 0.34 cycle by moving more models onto the Transformers backend
Recall becomes an official Claude connector, so your saved library feeds Claude's answers.
opencode keeps publishing process-daemon patches on protocol 8.
See all Khoj alternatives → · See all LobeChat alternatives →
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
They serve adjacent needs but don't currently overlap on shipped themes. LobeChat is currently shipping more aggressively (velocity 10.0 vs 0.0), 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. LobeChat is currently shipping more aggressively (velocity 10.0 vs 0.0), 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 Khoj alternatives in ai-assistants are ranked by recent ship velocity. Browse the "Khoj alternatives" section above for the current picks, or visit /alternatives/khoj for the full list with editorial commentary on each.
Top LobeChat alternatives in ai-assistants are ranked by recent ship velocity. Browse the "LobeChat alternatives" section above for the current picks, or visit /alternatives/lobe-chat for the full list with editorial commentary on each.