Tag
#ai-agents
-
Context Pruning: Shrink Data Before the Model
Context pruning filters, pages and sums API data in a sandbox before it reaches the model. Cloudflare Dynamic Workers make that sandbox cheap and quick.
-
Use a Credential Proxy to Keep Keys From Agents
A credential proxy keeps real API keys outside the agent. The agent sends a placeholder, and the proxy swaps in the secret only for allowed domains.
-
Agent Skills: Load Only the Instructions You Need
Agent Skills package instructions as folders with a SKILL.md file. Agents read a short description at startup and load the full skill only when needed.
-
Why Agent Infrastructure Is Moving to Rust
Codex CLI and the GitHub Copilot runtime both moved from TypeScript to Rust. What changed, the real 292 ms benchmark, and why density beats bragging rights.
-
Lightpanda PandaScript: Pay the LLM Only Once
Lightpanda's PandaScript lets an agent explore a site once with an LLM, then save the steps as plain JavaScript that replays with no model and no tokens.
-
Obscura: A Rust Headless Browser Built for Agents
Obscura is an open-source Rust headless browser that runs V8, speaks CDP for Puppeteer and Playwright, and uses a fraction of headless Chrome's memory.
-
Code Mode for MCP: Two Tools Instead of 2,594
Code Mode lets agents write code against an API instead of loading every MCP tool. Cloudflare covers 2,500+ endpoints with two tools and 1,000 tokens.
-
Always-On Agents Mostly Sleep, and That Works
Always-on agents are mostly asleep. Here is how an event inbox, timers, memory, permissions and an outbox let them wake, work in short runs and rest.
-
Decision Models: The Smart If for AI Agents
Decision models like TypeSafe's Jev and Convai's Laya return typed choices and probabilities instead of text, making agent routing fast and boring.








