Warp has come a long way since it initially set out to modernize the terminal. In the screenshot above, an agent is working through a plan alongside a developer's own shell commands — running its own commands, reasoning, proposing a diff — all in the same scroll stream. Five years ago, none of that would have had a place in Warp; today it's a core part of how people use it.
warp/CONTRIBUTING.md at master · warpdotdev/warp
Warp is an agentic development environment, born out of the terminal. - warpdotdev/warp
shepherd-agents/shepherd
A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write fork ~5x faster than docker commit, with ~95% KV-cache reuse on replay. Framework built for meta-agents to supervise, optimize, and train other agents
Warp on Twitter / X
To make this possible, Oz-managed agents do the heavy lifting (coding, planning, testing). This lets community members focus on ideas, direction, and verification.We believe this workflow will let us build a better Warp, faster.https://t.co/bsVk3DE61V 🔖 pic.twitter.com/KqvR6jkZ40— Warp (@warpdotdev) April 28, 2026
Writing code is cheap now - Agentic Engineering Patterns
Writing code is cheap now - Agentic Engineering Patterns
WarpBuild - 2x faster, 50% cheaper Github Actions runners
WarpBuild is a drop in replacement for Github runners that are 2x faster and 50% cheaper.
Joshua Gu on Twitter / X
Recent agentic systems (Claude Code, Codex, RLM, etc.) push context out of the prompt and into the environment (e.g., as files). This helps them maintain long-term knowledge about their goals and functionality.🚨 While this is a good idea, we show a surprising result: systems… pic.twitter.com/XHFVaDcr4l— Joshua Gu (@astrogu_) May 20, 2026
The Shape of Memory Benchmarks
Why the familiar memory benchmarks are outdated, how the agent-native work looks today and why design your own.
The Agent Harness
A specification for agent behavior that LLM frameworks leave undefined: error handling, context management, tool execution, and state transitions.
First impressions: Delta - Cameron's writing
A look at Zed's new agent development tool.
ndrstnd: understand what your coding agent actually did
A local comprehension workspace that turns agent-produced branch diffs into an evidence-linked story.
Agents Done Right: A Framework Vision for 2026
Agents choke on context, loop on failures, and dump walls of code for review. It's time to rethink the architecture.
Mistral Vibe | AI coding agent for terminal, IDE by Mistral.
Agentic coding that understands your entire codebase. Build, test, and modernize autonomously.
The Gap Through Which We Praise the Machine
My current theory of agentic programming: people are amazing at adapting the tools they're given and totally underestimate the extent to which they do it, and the amount of skill we build doing that is an incidental consequence of how badly the tools are designed.
