Paradev: Run 100+ Coding Agents in Parallel for Free
Paradev lets you run Claude Code, Codex, and Gemini CLI in parallel git worktrees on your machine. Free forever for local use. 15.8K ...
FreeToken: Run a 290B MoE Model on One Gaming GPU
FreeToken lets you run 290B+ MoE models on a single consumer GPU. Here's how the ...
Anthropic Message Threads Beta: Stop Resending Conversations
Anthropic's Message Threads beta lets Claude agents send only new messages per turn, cutting TTFT ...
DeepSeek Super-Agent Opens PRs Without Being Asked
DeepSeek open-sourced dsh-superagent, a proactive coding agent that monitors GitHub, picks up bug reports, and ...
Memdoor: Five Small Models Just Beat a Frontier Coding Model
Memdoor runs five Qwen3.8-27B agents as a coordinated team and outscores Claude Fable 5 on ...
OpenAI Kills Agent Builder, Evals API, and Stored Prompts — Nov 30 Checklist
OpenAI shuts down Agent Builder, the Evals API, and v1/prompts on November 30. Here is the migration checklist for each — including the ...
Claude Code’s Game-Clone Rule Is Blocking Developers
Anthropic added two sentences to Claude Code's Opus 5.5 on October 27 to stop AI-assisted ...
Gemini 4 Argon API Prices Double December 1: Migration Checklist
Google doubles Gemini 4 Argon API prices on December 1. Input goes from $2 to ...
Cloudflare’s triagebot-action Cut Astro’s Issues by 85%
Cloudflare just open-sourced the four-agent pipeline that slashed Astro’s GitHub issue backlog from over 200 ...
OpenAI Jalapeño Chip: What 50% Cheaper Inference Means
OpenAI's Jalapeño ASIC claims 50% cheaper inference than Nvidia GPUs. Here's what it actually means ...