Glad Labs fixed a GPU pinning issue where LiteLLM 1.89.2's global api_base override prevented per-model routing, causing vision tasks to cold-load onto the wrong GPU. The team also hardened content gu…
A developer building Bastra Recall, an MIT-licensed MCP memory server for Claude, discovered that their initial 98.3% benchmark was misleading because it queried each memory with its own trigger phras…
A developer built a Go library for semantic LLM caching that combines deterministic hashing with vector similarity search to reduce costs from repeated but differently worded queries. The library supp…
Felix Kjellberg (PewDiePie) released Odysseus, an open-source, self-hosted AI workspace bundling chat, agents, research, and local model workflows under an AGPL-3.0 license. The project, launched in M…
A developer built session-indexer, a Go tool that indexes Claude Code session transcripts into a per-project SQLite database for semantic memory retrieval. The tool avoids centralized memory stores by…
Qwen open-sourced the 35-billion parameter Mixture of Experts model Qwen 3.6-35B-A3B, which activates only 3 billion parameters per token and runs on a $599 Mac Mini M4 with 16GB RAM at 17 tok/s with …
Loomcycle released versions 1.9.0 to 1.11.1 with four major arcs: a security hardening pass closing 17 findings, a new CredentialDef system for encrypted per-tenant secrets using AES-256-GCM, cost att…
OrinIDE v1.0.8, an AI-powered code editor that runs entirely in the browser without cloud accounts or subscriptions, now supports offline AI models via Ollama and introduces a 4-agent workflow for pla…
SmolSignal, an AI signal copilot for Flipper Zero, launches to help users analyze capture files with plain-English explanations and safety classifications. The tool reads multiple file formats, detect…
Solon 4.0's ReActAgent enables developers to build AI agents that reason, use external tools, and adapt based on real-world feedback. The agent implements a cognitive loop of thought, action, and obse…
Solon 4.0 introduces ChatModel, a unified LLM client that abstracts away boilerplate code for integrating large language models into Java applications. The API supports multiple model providers includ…
Gavio, an open-source interceptor pipeline for production LLM applications, has been released. The tool sits between applications and LLM providers, offering PII protection, audit trails, reliability,…
Billy, a self-hosted AI assistant that lives in Telegram, has been released. It runs locally via Ollama or in the cloud, uses Anthropic Claude as its brain, and can manage email, CRM, documents, and r…
Jamesob's guide provides developers with actionable strategies to deploy state-of-the-art large language models locally on consumer-grade hardware. The framework covers model quantization, pruning, ef…
A security researcher warns that coding models should be treated as executable code, as they can generate malicious tool calls that exfiltrate environment variables or introduce subtle vulnerabilities…
OmniRoute, an open-source AI gateway, has released version 3.8.42, enabling developers to connect to over 236 AI providers through a single API endpoint. The tool offers automatic failover, token comp…
Llama.cpp users can significantly improve inference speed and output quality by tuning sampling parameters such as temperature, TopP, MinP, TopK, repeat penalty, DRY, XTC, Dynatemp, Adaptive-P, and Mi…
CorvinLabs released CorvinOS, a self-hosted agentic operating system that enforces EU AI Act and GDPR compliance in code, not documentation. The open-source platform connects multiple LLMs to seven me…
A developer created a daemon to reduce GPU temperatures on the NVIDIA DGX Spark by clock-locking via nvidia-smi -lgc. The daemon samples temperature every 30 seconds and adjusts clock ceilings, droppi…
Researchers at Zenity documented three campaigns between March and May 2026 where attackers hijacked exposed LLM endpoints from Ollama and LiteLLM instances to run offensive AI operations. The attacks…