LLM Inspector, a new open-source CLI tool from developer Helal Saoudi, analyzes live LLM inference processes to show exactly how GPU memory is used by weights, KV cache, and workspace, then projects o…
Glamorous Toolkit is a moldable development environment designed to help humans and AI make sense of large systems and AI-generated code by replacing code reading with deterministic contextual tools. …
Schemity, a desktop ERD tool, now offers a bring-your-own-key (BYOK) AI chat that sends schema design requests directly from the user's machine to their chosen provider—OpenAI, Claude, Gemini, or Deep…
A developer built footnote-mcp, a Python MCP server that verifies source claims using heuristic and LLM backends, achieving 100% accuracy on numeric and factual data claims. The server supports multip…
A developer successfully ran Google's Agent Development Kit (ADK) with the locally hosted Gemma 4 model via Ollama, building a weather agent that uses tool calling to orchestrate Google Maps and Open-…
Drun, an open-source ephemeral runtime platform for agentic workflows, virtualizes host components into sandboxed workspaces with git-like primitives for parallel trajectory exploration and dead-end d…
A new benchmark and tutorial series from developer dotnetspark reveals that model-routing systems optimize the wrong axis by routing queries to models without grounding, finding that a cheap local mod…
Spring AI 2.0 introduces self-correcting structured output that automatically retries when an LLM returns invalid JSON, fixing errors like null primitives or missing fields. The feature, demonstrated …
Mlx-serve, an open-source native LLM inference server for Apple Silicon written in Zig, shipped an update that adds compatibility with the Ollama API alongside existing OpenAI and Anthropic API suppor…
A developer built a 100% local personal assistant using Ollama, LangChain, and voice, running entirely on a laptop GPU with no API calls. The project exposed key differences between cloud-based 70B+ m…
A developer running 30 projects across 5 AI models describes how Anthropic's limited-time promotional access to Claude Fable 5 forced a routing discipline that maximized the model's scarce allocation.…
The open-source agent framework goose, built at Block and hosted by the Agentic AI Foundation under the Linux Foundation, can run fully offline on an NVIDIA DGX Spark with 128 GB of unified memory, us…
A developer building SAGE GUI Electron, a local-first desktop app for AI coding workflows, announced the project after receiving over 2,000 clones. The app tracks command output, compresses noisy logs…
Qelvora, a new macOS utility built by directing Codex, corrects, rewrites, and translates selected text using local Ollama models, ensuring privacy by keeping all processing on the user's Mac. The too…
A developer built Aura Memory, an open-source cognitive memory runtime that treats memory as a governed layer separate from the model, enabling AI agents to manage persistence, retrieval, lifecycle, a…
EasyDocs, an open-source tool by Ruben Gonzalez, generates accurate OpenAPI 3.0 specs from real API traffic using an AI model, running entirely on the user's machine with no data sent externally. The …
A developer shows how to build, test, and deploy an AI agent using Ollama and FastAPI in under an hour. The agent uses the phi3 model and is exposed via a FastAPI endpoint that forwards requests to th…
A developer automated their entire dev workflow using AI agents running 24/7 on a Mac Mini M4, achieving a total monthly cost of about $13 compared to $300-400 for cloud alternatives. The system, name…
A developer shows how to build a local PDF summarizer using Ollama and Llama 3, keeping documents private and avoiding per-token costs. The approach uses open-source LLMs running on local hardware, wi…
Scribe is a new CLI tool that builds a cross-project knowledge base for AI coding agents by mining git history, Claude Code and Codex sessions, and self-sent URLs, then writing a curated markdown wiki…