A developer built a Trigger.dev connector for Cognee, the open-source memory layer for AI agents, that syncs background job history — schedules, errors, failed runs and deployments — into searchable m…
A Google Developer Expert for Firebase published a hands-on implementation guide for Firebase AI Logic, a service that lets web and mobile clients call Gemini and Imagen models through the Firebase We…
Firebase released Genkit Monitoring, production observability tooling that automatically collects telemetry from Genkit AI features and surfaces usage, success rates, p95 latency and input/output toke…
A ReclaimLLM analysis finds that running local LLMs via Ollama only prevents prompt leakage to third-party inference APIs when inference stays on-device, the server is not network-exposed, and cloud-b…
Developer Neha Bohra built GhostShell, an open-source, local-first terminal command analyzer that uses a rule engine for deterministic risk classification and an Ollama-served language model to explai…
A developer built POSSESSED, a playable experiment demonstrating indirect prompt injection against an AI browser agent, in which a user rewrites an archive note to try to make a Gemma-powered assistan…
A full-stack developer fine-tuned Qwen2.5-1.5B-Instruct on 80,000 Egyptian Arabic examples using QLoRA, raising Egyptian dialect fluency from 3.1/5 to 4.6/5 in a single epoch at the cost of a roughly …
Developer Islam Al-Nashar re-uploaded Qwen's Qwen-Image-2.1 model to Hugging Face as ISLAM-PO/Glitch-Img-1.0, keeping all weights and configs unchanged while adding documentation and a demo Space. The…
A developer outlines a four-stage AI code review workflow that places a linter first, scopes an LLM strictly to the diff, and keeps a human as the sole merge approver. The approach targets the two com…
A developer built GhostTrace (Java Edition), an offline-first terminal companion that wraps a JLine 3 REPL in a haunted persona and runs local AI through Ollama with an offline fallback. The tool inte…
A developer built Ofrenda AI, an open-source, offline-first digital Día de los Muertos altar and oral history vault powered by Google Gemma 2 and ElevenLabs. The project runs locally via a Python serv…
Google announced on October 30, 2026 that it will support a shared AI training control in robots.txt, built on work from the IETF's AIPREF working group, with Microsoft and OpenAI reported to honor it…
IP99 by ThreatHunter publishes an OpenAPI 3.1 document at a stable URL, letting developers import its IP risk and geolocation API directly into Postman, Insomnia, openapi-generator, or a GPT Action in…
The DevUtils MCP Server project released v1.1.0, a local Model Context Protocol server exposing 36 developer utilities — hashing, encoding, ID generation, JWT inspection, JSON formatting, network calc…
A developer built Echoes Beyond, an offline-first AI memory preservation project that organizes old photographs, voice recordings, letters and personal stories into a searchable archive and generates …
A developer built Corvus, a local-first AI workspace that runs Google's open-weight Gemma models through Ollama entirely on the user's own machine, streaming replies word by word with no API keys, acc…
A developer published a guide for building a streaming AI chat interface in React using shadcn/ui, the Vercel AI SDK, and four open-source components from Cuelark UI (Conversation, Message, StreamingT…
A developer built Socratic Duck, a rubber-duck debugging companion powered by Google's Gemma 4 that answers developer questions only with Socratic prompts, never the fix. The tool runs every model rep…
Google DeepMind released Gemini 4 Carbon, which ranks first on the Artificial Analysis Intelligence Index with gains in coding, agentic and long-horizon tasks, initially gated to cyber defenders and s…
A developer built Skill Airlock, an open-source auditor that scans AI agent skills — both scripts and Markdown instructions — and assigns CLEAN, OK, REVIEW or BLOCK verdicts with file:line locations. …