DeepMem, a drop-in AI memory layer compatible with the Mem0 API, claims 2× faster response times and 10× lower cost, with self-hosted options at $0 and cloud plans starting at $1.9/month compared to M…
Morten Punnerud-Engelstad released mpe-lkg, a local knowledge graph tool that visualizes a language model's step-by-step reasoning using Ollama and embeddings, with blue edges for embedding similarity…
Marcel Petrick released Agentic Swear Jar, a private, local, zero-AI dashboard that analyzes profanity in Claude Code and Codex CLI histories, with no prompts uploaded and no runtime dependencies beyo…
Mainline, an open-source, science-based chess training app, is now in closed beta, offering adaptive training programs that adjust to users' games, time budgets, and goals. The app, licensed under AGP…
A developer has published a step-by-step guide for running a 4B parameter LLM locally on a Mac, using Mozilla's llamafile and a fine-tuned Qwen3 model from Hugging Face. The process involves downloadi…
Vercel released a minimal chatbot template built with Next.js, the AI SDK, shadcn/ui, shadcn/react, shadcn/typeset, and the Vercel AI Gateway, featuring streaming chat with markdown rendering, tool ca…
Brave Software released brave-mcp, a Model Context Protocol server that gives Claude Code, Codex, Cursor, OpenCode, and other MCP clients native access to Brave for browser automation, network and con…
Temple Compute released Pantheon, a collection of production-ready scientific workflows for its Horus Runtime, covering molecular dynamics, virtual screening, docking, and LLM training. The workflows …
Archon, an open-source workflow engine for AI coding agents, has been released to make AI coding deterministic and repeatable by defining development processes as YAML workflows. The tool, created by …
Tynx, a new ONNX runtime with a PyTorch-shaped API for inference and training, has been released as a Python package under 20 MB. Written in Rust, it uses Burn/CubeCL and wgpu for GPU execution across…
Pragma, a code-public desktop application for orchestrating multiple AI agents, was released as a preview on GitHub, allowing users to combine agent harnesses, models, tools, and context sources into …
Developer choiyounggi released Dev-loop, a Claude Code plugin that combines a TDD/PDCA/Reflexion verification loop with a semantic-layer knowledge base of software best practices, enabling supervised …
SCQOS, an open-source pre-execution governance architecture, determines whether an action, state, workload, process, or computation is admissible before execution, reversing the traditional 'execute f…
A new experimental framework called Semantic Thermodynamics found that a two-stage LLM architecture using a semantic micro-router before a large executor outperforms a single large-model call, cutting…
SpotWarp v3.2, a 100% local Python daemon, provides sub-minute cross-cloud failover between Vast.ai and RunPod for spot GPU evictions, saving up to 70% on GPU compute bills. Testing uncovered 5 real b…
Askance, a new human-in-the-loop GUI for agentic coding, lets developers answer questions from AI coding agents like Claude Code via a local server and CLI, with support for Markdown, Mermaid diagrams…
Playcall, an open-source alternative to Gong, grades whether sales calls were right for the specific buyer, using Next.js 16, React 19, Supabase, and the Vercel AI SDK with OpenAI, Anthropic, and 15 o…
A developer's local-first memory tool for coding agents returns a result 67.9% of the time even when asked a question from a different project, revealing that its relevance floor cannot distinguish an…
A working prototype plugin for Claude Code, named Claudish to English, rewrites assistant messages into plain English using a local LLM via ollama, and is display-only, preserving the original text in…
Listen Notes has released microfeed, an open-source, agentic content management system (CMS) that self-hosts on Cloudflare's Workers, R2, and D1, allowing users to publish audio, video, photos, docume…