opencode
opencode's feed goes quiet after V2 took over, with only CI and animation tags.
A side-by-side editorial comparison of Baseten and Jan — release velocity, themes, recent moves, and the top alternatives to consider.
Baseten ends the free launch of elephant-1 and mammoth-1 and adds per-replica metrics.
Baseten's newest entries are commercial and operational. The elephant-1 and mammoth-1 classification models, launched free on October 21, moved to paid usage on Model APIs from October 27, and workspaces can now compare CPU, GPU and memory per replica to find outliers that aggregate graphs hide. The week before was mostly security: API keys unused for 30 days are revoked automatically, auth errors switch from 403 to 401 on October 28, and users were told to upgrade CLIs after the eMudhra CA compromise.
Jan is quietly wiring subagents into the same tool pipeline its main agent uses.
Jan's tagged releases in this window are small: a persisted chain-of-thought duration, a CSP fix that unblocks video uploads, and a change to llama.cpp defaults that turns auto-fit off and pins context length to 8192. Cadence is slow — four tags spanning May to July. The most recent tag is not a release at all but a development checkpoint.
Baseten's newest entries are commercial and operational. The elephant-1 and mammoth-1 classification models, launched free on October 21, moved to paid usage on Model APIs from October 27, and workspaces can now compare CPU, GPU and memory per replica to find outliers that aggregate graphs hide. The week before was mostly security: API keys unused for 30 days are revoked automatically, auth errors switch from 403 to 401 on October 28, and users were told to upgrade CLIs after the eMudhra CA compromise.
Baseten keeps adding models to Model APIs on a free-then-paid launch pattern, while building out observability for dedicated deployments: GPU temperature and utilization a week ago, per-replica breakdowns now. The security tightening of late October appears to have settled into defaults.
Expect further Model API additions following the same free launch window before paid usage, and more per-replica or per-worker debugging tools for dedicated deployments.
Jan's tagged releases in this window are small: a persisted chain-of-thought duration, a CSP fix that unblocks video uploads, and a change to llama.cpp defaults that turns auto-fit off and pins context length to 8192. Cadence is slow — four tags spanning May to July. The most recent tag is not a release at all but a development checkpoint.
That checkpoint is the informative one: subagents now reuse the main native tool pipeline rather than a separate path, alongside code-UI work. Jan is consolidating on one tool-calling surface for both the primary agent and its subagents, which is the precondition for multi-agent workflows inside a local desktop app. The shipped releases meanwhile read as stabilization of the chat surface — durable metadata, predictable inference defaults.
The subagent and code-UI work visible in the checkpoint tags should surface in the next minor release; on this cadence, expect more 0.8 stabilization patches before it does.
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 Baseten or Jan.
opencode's feed goes quiet after V2 took over, with only CI and animation tags.
Ollama v0.40.11 adds local speech output on macOS, with an OpenAI-compatible audio endpoint.
Copilot adds GPT-6.1 Terra as a cheaper agentic default and makes assisted permissions GA.
LobeHub canary.3 adds Projects with a lead agent, multi-file Canvas artifacts and Docs.
Claude Duet opens a proactive-agent app to Pro and Max, the first move after the 5.5 rollout.
DocsBot publishes an e-commerce case study while waiting for its November launch week.
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
They serve adjacent needs but don't currently overlap on shipped themes. Baseten and Jan are shipping at a similar cadence (velocity 5.0 vs 5.0, both within Sparkpulse's "active" band). 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. Baseten and Jan are shipping at a similar cadence (velocity 5.0 vs 5.0, both within Sparkpulse's "active" band). For your specific use case, the alternatives sections above list other ai-assistants products to evaluate alongside.
Top Baseten alternatives in ai-assistants are ranked by recent ship velocity. Browse the "Baseten alternatives" section above for the current picks, or visit /alternatives/baseten for the full list with editorial commentary on each.
Top Jan alternatives in ai-assistants are ranked by recent ship velocity. Browse the "Jan alternatives" section above for the current picks, or visit /alternatives/jan for the full list with editorial commentary on each.