<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Release on LocalAI</title><link>https://localai.io/tags/release/</link><description>Recent content in Release on LocalAI</description><generator>Hugo</generator><language>en-GB</language><lastBuildDate>Wed, 18 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://localai.io/tags/release/index.xml" rel="self" type="application/rss+xml"/><item><title>LocalAI 5.0: your AI does the work, you keep the files</title><link>https://localai.io/blog/localai-5-0/</link><pubDate>Wed, 18 Nov 2026 00:00:00 +0000</pubDate><guid>https://localai.io/blog/localai-5-0/</guid><description>Run open models for chat, images, speech and video on your own machines. The API speaks the OpenAI and Anthropic formats. 5.0 adds Projects, a desktop app for macOS and Linux, and documents, files and team sharing.</description></item><item><title>What landed in LocalAI 4.11</title><link>https://localai.io/blog/what-landed-in-localai-4-11/</link><pubDate>Fri, 02 Oct 2026 00:00:00 +0000</pubDate><guid>https://localai.io/blog/what-landed-in-localai-4-11/</guid><description>Remember speakers, configure model failover, and inspect the models running on one LocalAI host.</description></item><item><title>What landed in LocalAI 4.9</title><link>https://localai.io/blog/what-landed-in-localai-4-9/</link><pubDate>Thu, 20 Aug 2026 00:00:00 +0000</pubDate><guid>https://localai.io/blog/what-landed-in-localai-4-9/</guid><description>Authentication now denies by default, chat can compress its own history, models and backends each got one page, and vllm-cpp builds for cards other than Blackwell. 146 pull requests in thirteen days.</description></item><item><title>What landed in LocalAI 4.8</title><link>https://localai.io/blog/what-landed-in-localai-4-8/</link><pubDate>Tue, 04 Aug 2026 00:00:00 +0000</pubDate><guid>https://localai.io/blog/what-landed-in-localai-4-8/</guid><description>A new inference engine, a terminal agent in the CLI, 3D generation, and a web interface 3.48x lighter. 386 pull requests in twenty-two days.</description></item><item><title>LocalAI 4.3: signed backends, and the prompt cache that was off</title><link>https://localai.io/blog/what-landed-in-localai-4-3/</link><pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate><guid>https://localai.io/blog/what-landed-in-localai-4-3/</guid><description>Keyless cosign verification for backend OCI images, the llama.cpp prompt cache enabled by default, per-API-key usage attribution, and the replica-pinning bug that kept a second node idle.</description></item><item><title>LocalAI 4.2: who spoke when, and whose face is that</title><link>https://localai.io/blog/what-landed-in-localai-4-2/</link><pubDate>Mon, 11 May 2026 00:00:00 +0000</pubDate><guid>https://localai.io/blog/what-landed-in-localai-4-2/</guid><description>A /v1/audio/diarization endpoint, voice and face recognition with liveness, a drop-in Ollama API, and eleven new backends.</description></item><item><title>LocalAI 4.1: more than one box, and more than one user</title><link>https://localai.io/blog/what-landed-in-localai-4-1/</link><pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate><guid>https://localai.io/blog/what-landed-in-localai-4-1/</guid><description>Distributed cluster mode that places requests by real free VRAM, OIDC with per-user API keys and quotas, and LoRA fine-tuning that exports straight to GGUF.</description></item><item><title>LocalAI 4.0: agents in the core, and a React interface</title><link>https://localai.io/blog/what-landed-in-localai-4-0/</link><pubDate>Sat, 14 Mar 2026 00:00:00 +0000</pubDate><guid>https://localai.io/blog/what-landed-in-localai-4-0/</guid><description>Native agent orchestration with the Agenthub, a rewritten interface with Canvas mode, MCP Apps with tool streaming, and two things removed.</description></item><item><title>LocalAI 3.10: the Anthropic and Responses APIs, and one image for every GPU</title><link>https://localai.io/blog/what-landed-in-localai-3-10/</link><pubDate>Sun, 18 Jan 2026 00:00:00 +0000</pubDate><guid>https://localai.io/blog/what-landed-in-localai-3-10/</guid><description>A /v1/messages endpoint that Claude clients can talk to unchanged, Open Responses compatibility that passes the official acceptance tests, and GPU libraries moved inside the backend containers so one image works on any hardware.</description></item></channel></rss>