Search the publication

Results for “Open models”

Showing 73–80 of 80 · latest 80 stories

Open models

06Local LLMs

Aug 23, 20262 min read

Daimon: Local Proxy Redacts Sensitive Prompts Before External Large Language Model Inference

Daimon is an open-source local proxy that intercepts LLM requests to sanitize credentials and private identifiers before sending them to external providers. Once the remote response returns, Daimon restores the original local data automatically.

06Local LLMs

Jun 30, 20262 min read

Deploying Qwen 3.6 27B for Local AI Development

Qwen 3.6 27B is a robust, dense open-weight model suitable for local development. Using llama.cpp with 8-bit quantization enables efficient execution on Apple Silicon and Nvidia hardware.

07Local LLMs

Aug 11, 20262 min read

NVIDIA Releases Nemotron 3.5 Lightning 30B MoE Model for Local Agents

NVIDIA released Nemotron 3.5 Lightning, an open 30B Mixture-of-Experts model with 3B active parameters and a 1M context window. It is available on Ollama and optimized for always-on background execution harnesses.

09Token & cost optimization

Aug 31, 20262 min read

GLM-5.3-Flash Slashes Agentic Inference Costs by up to 50x

Zhipu AI revealed that its unannounced Ox Alpha model on OpenRouter is GLM-5.3-Flash. It delivers frontier-grade coding performance at $0.15 per million input tokens and $0.50 per million output tokens under an MIT license.

01Tools & releases

Sep 23, 20262 min read

Anthropic Launches Claude Opus 5.5 with Lower Pricing and Agentic Coding Gains

Anthropic released Claude Opus 5.5, delivering Claude Fable 5.1 capability levels at 40% lower operational cost. Input tokens now cost $4 per million, while prompt-cache reads drop 60% to $0.20 per million.

03Vibe coding workflow

Jun 2, 20262 min read

Stanford Computer Science course releases strict Model Context Protocol guidelines for agentic code management

Stanford's CS336 course has published its official CLAUDE.md guidelines for AI agents. This developer cheatsheet outlines styling, command executions, and state management rules to prevent agents from breaking project structures. Implement these patterns inside your local workspaces.

04Agents & MCP

Oct 4, 20262 min read

Running Codex Computer Use Inside Claude Code via Model Context Protocol

Codex's background computer-use automation engine runs as an unbundled local Model Context Protocol server on macOS. Claude Code can directly call this server headless to click and drag without stealing the user's cursor.

05Agents & MCP

Sep 8, 20262 min read

Forgejo Model Context Protocol Server Reaches Version 3.0.0 for Self-Hosted Repositories

The agentic-forges project released forgejo-mcp v3.0.0, exposing Model Context Protocol endpoints for self-hosted Forgejo and Gitea code platforms. The update enables IDE agents like Claude Code, Cursor, and Codex to interface with private Git repositories without routing source code through external clouds.