September 22, 2026
Open WebUI fixes access control; Redis outages still permit revoked tokens, per release notes.
Worth mentioning
1.
Open WebUI fixes access control; Redis outages still permit revoked tokens, per release notes.
v0.11.4 — ### Added - 📉 **Far smaller slim image.** A slim build now comes down at around 175 MB, near enough 89% smaller than the last release, the local models, the packages around them and the tools that installed them all gone from it; what that…
⚠ Uncertainty: Primary linked page read; claims not independently reproduced.
2.
LlamaIndex release notes describe tool retry, streaming, and dependency security fixes.
v0.14.25 — # Release Notes ## [2026-09-21] ### llama-index-agent-agentmesh [0.3.0] - fix: resolve a ton of security alerts (#22855) ### llama-index-agent-azure [0.4.0] - fix: resolve a ton of secu…
⚠ Uncertainty: Primary linked page read; claims not independently reproduced.
3.
DeepSeek adapter fixes dependency compatibility, strict-mode routing, and cache accounting.
langchain-deepseek==1.1.1 — Changes since langchain-deepseek==1.1.0 fix(deepseek,infra): resolve compatible minimum OpenAI dependencies, bump min ver (#40738) release(deepseek): 1.1.1 (#40734) chore(deps): bump anyio from 4.11.0 to 4.14.2 in /libs/partners/deepseek (#…
⚠ Uncertainty: Primary linked page read; claims not independently reproduced.
4.
Neon adds branch-scoped function schedules compatible with scale to zero.
Your Neon Functions can now run on a schedule — During the beta phase, the only way to run a Neon Function was to send it an HTTP request. That works well for jobs triggered by your app, but not so much for backend jobs. If you wanted to pull an external API into Postgres every 15 minute…
⚠ Uncertainty: Primary linked page read; claims not independently reproduced.
5.
OpenAI adapter exposes inferred Responses routing and adds request-constraint support.
langchain-openai==1.6.3 — Changes since langchain-openai==1.6.2 release(openai): 1.6.3 (#40719) fix(openai): expose inferred Responses API routing at initialization (#40715) chore(deps): bump anyio from 4.11.0 to 4.14.2 in /libs/partners/openai (#40629) fix(openai):…
⚠ Uncertainty: Primary linked page read; claims not independently reproduced.
6.
Neon adds branch-specific custom domains with automatic TLS; function traffic remains billable.
Custom domains for Neon Functions — During beta, each Function was reachable only at its Neon invocation URL, something like `https://br-cool-forest-a1b2c3d4-api.compute.c-2.us-east-2.aws.neon.tech`. Now, we support custom domains - you can put it behind `api.example.com` ins…
⚠ Uncertainty: Primary linked page read; claims not independently reproduced.
Monitor
7.
LangChain core marks chat message history deprecated; inspect usage before upgrading.
langchain-core==1.6.4 — Changes since langchain-core==1.6.3 release(core): 1.6.4 (#40718) chore(core): deprecate chat message history (#40711) chore(deps): bump anyio from 4.12.0 to 4.14.2 in /libs/core (#40634) chore(deps): bump soupsieve from 2.8.4 to 2.9 in /li…
⚠ Uncertainty: Primary linked page read; claims not independently reproduced.
8.
Lossless-memory preserves raw logs; single-user operation and Japanese-only relative-date parsing.
Show HN: Lossless-memory – a personal AI memory that never summarizes —
⚠ Uncertainty: Primary linked page read; claims not independently reproduced.
40 researched links (full index)
Get this every morning
Filtered from 40+ sources daily — what changed, why it matters, what to do. Free.
Free. Unsubscribe any time.