All News

Headroom: Open-Source Proxy That Cuts LLM Token Costs Up To 90%

Headroom: Open-Source Proxy That Cuts LLM Token Costs Up To 90%

Headroom is an open-source proxy that compresses, caches, and manages LLM inputs and outputs to cut token usage and provider costs. It provides reversible compression (SmartCrusher/CCR), prefix stabilization, rolling-window context, and a drop-in proxy + SDK with no code changes.

tool cover
Tool

agent-browser: Fast Rust CLI and Playwright Daemon for AI Agents

agent-browser pairs a fast Rust CLI with a Node.js Playwright daemon to provide deterministic, AI-friendly browser automation via snapshots and refs. It offers semantic locators, JSON output for LLMs, session isolation, network mocking, and headed/CDP modes.

Anthropic's Cowork Brings File-Based 'Agency' to Claude Max on macOS

Anthropic's Cowork Brings File-Based 'Agency' to Claude Max on macOS

Anthropic's new Cowork research preview lets Claude access and edit a chosen local folder, enabling multi-step tasks like reorganizing files, extracting expenses, or drafting reports. It's available now to Claude Max macOS users with explicit access and safety prompts.

Warp 2.0: Agentic Development Environment Unifies Code, Agents, Terminal

Warp 2.0: Agentic Development Environment Unifies Code, Agents, Terminal

Warp 2.0 launches an Agentic Development Environment that merges coding, terminal commands, AI agents, and a shared team Drive into one desktop app. It emphasizes prompt-first workflows, multithreaded agent management, granular autonomy controls, and local-first privacy.

GLM-4.7 on Cerebras: Real-Time Coding AI at Record Speed

GLM-4.7 on Cerebras: Real-Time Coding AI at Record Speed

GLM-4.7 on Cerebras Inference Cloud boosts code generation, agent planning, and long-session reliability for developer workflows. On Cerebras hardware it hits a whopping 1000 tokens per seconds and claims up to 10× price-performance versus Claude Sonnet 4.5.

Showing 1 to 5 of 152 results