Z.ai's open-weights GLM-5.2 model (744B MoE, 1M-token context) is available for free via web chat and a rate-limited API through OpenRouter, with no credit card required. For developers, the free API …
A new AI model matching Opus 4.8-level performance is now available for free local execution, according to a newsletter. The update also includes OpenRouter Fusion, GLM-5.2 local deployment, and Loop …
The AI industry's focus on token cost or quality alone is misguided, advocating instead for a 'Value For Money' philosophy that balances cost, quality, and risk. It critiques current trends like 'Toke…
Z.ai's GLM-5.2, a 756B-parameter model with a 1M-token context window, competed against Claude Opus in a Tech Stackups test building a 3D platformer in raw WebGL. Claude Opus finished in 33m 30s at an…
A developer built audit.sh, a Web3 security auditing platform that treats large language models as collaborative team members rather than passive tools. The platform integrates specialized AI agents—C…
A developer built a personal intelligence system that curates GitHub and news using an LLM, delivering three scheduled briefings to Telegram. The system, hosted on a budget VPS, uses OpenRouter for LL…
Moonshot AI released Kimi K2.7 Code, a 1-trillion-parameter open-source coding model that uses 30% fewer reasoning tokens than its predecessor and outperforms Claude Opus 4.8 on MCP tool-calling bench…
Meerkat, an open-source API, launches to help developers process asynchronous tasks like link monitoring and delivery tracking without building schedulers or webhook plumbing. The platform allows self…
Zhipu AI's GLM 5.2 coding model can be used as a cost-effective backend for AI agents via OpenRouter, offering strong code generation and reasoning at 10-20% of the cost of Claude Sonnet or GPT-4o. Th…
Subagents are critical for cost, context management, and speed in AI agent harnesses, yet implementations vary widely across labs. The author examines subagent primitives including tool handoff, one-s…
Andrew Marble argues that switching from proprietary large language models to open models carries minimal professional risk, as open models now trail leaders like Claude and GPT by only a few months a…
OpenRouter launched Fusion API on June 13, an API that routes prompts to multiple AI models in parallel and synthesizes outputs, days after the U.S. government forced Anthropic to pull its Fable 5 and…
A new benchmark called FunnyBench tests AI models' ability to tell funny jokes by asking each model to generate ten jokes and letting users vote on their humor. The live leaderboard uses a Bayesian sc…
Chinese AI developers are slashing compute costs by up to 97% through architectural innovations like sparse MoE and FP8 training, reshaping global AI pricing under US export controls. DeepSeek trained…
A self-taught delivery rider from China built a multi-expert AI system that runs multiple LLM-powered expert agents in parallel, enabling cross-validation and debate. The MVP, developed after learning…
WhatsKept, a new open-source tool, extracts and decrypts WhatsApp history from iOS backups into a searchable local database that AI coding agents can query directly. The Go-based binary handles backup…
A developer built an open-source AI tool that reduces compliance paperwork for financial advisors from 2 hours to 3 minutes. The system uses a four-stage pipeline with local Whisper transcription, Cla…
A developer built ccglass, an open-source local observability tool that captures and displays AI coding agent requests and responses. The tool runs as a local proxy, allowing users to inspect model tr…
Rising AI compute costs are driving enterprises to adopt cheaper Chinese models like DeepSeek, with U.S. developers reporting costs of $10 per hour on Claude versus under $0.50 on DeepSeek. Companies …
A developer fixed a broken fallback chain in their OpenClaw agent that was causing request timeouts during peak hours. The new chain includes seven entries: two local Ollama models, three OpenRouter f…