Tools for this
Browse all ->
Work with Claude directly in your codebase. Build, debug, and ship from your terminal, IDE, Slack, web, and more.
The same powerful coding agent—now in ChatGPT.
Turn ideas into code
The open source AI coding agent
Agentic Infrastructure
Devin, the AI software engineer
Command your craft
The Open Source AI Coding Agent for VS Code, JetBrains, and your CLI
Fresh stories
Study finds context compactors retain only 17% of standing agent rules
A University of Pennsylvania study found common compactors retained only 17% of standing session rules while preserving task information. Practitioners use verified Markdown handoffs and background compaction to manage long coding-agent runs.
Study finds 307 agent-skill failures, including 125 functional failures
A study summary reports 307 confirmed failures caused by agent skills, including 125 functional failures. Practitioners favor user-invoked skills to avoid ambiguous automatic triggers and token use before a skill is needed.
Composio and Ante benchmark coding agent harnesses with 47%–67% success range
Composio and Ante tests reported that the same models behaved very differently by harness. DeepSeek V4 Flash ranged from 47% to 67% task success and $0.019 to $0.104 per task across harnesses.
Study finds context compactors retain only 17% of standing agent rules
A University of Pennsylvania study found common compactors retained only 17% of standing session rules while preserving task information. Practitioners use verified Markdown handoffs and background compaction to manage long coding-agent runs.
Cursor opens Origin code hosting beta with GitHub mirroring
Cursor Origin adds Git repository hosting, GitHub mirroring, pull requests, reviews, and agents that can edit code and push branches. The service is rolling out in early beta for paid plans.
GitHub users report outage disrupting commits and Actions
Users reported failures retrieving commits, running Actions, and syncing GitHub-hosted repositories. Some developers said the disruption blocked pull-request merges amid broader reliability complaints.
OpenCode Go adds $30 usage credit to its $10 plan
OpenCode revised its Go plan to include $30 in usage for a $10 subscription. The change follows a provider price increase and the company’s effort to secure lower-cost capacity.
Study finds 307 agent-skill failures, including 125 functional failures
Codex opens 1M-token GPT-5.6 Sol context for ChatGPT subscribers
OpenCode Go revises limits after DeepSeek price increase
Composio and Ante benchmark coding agent harnesses with 47%–67% success range
Briefs forAugust 17
Daily AI Digest
Get the best stories delivered
to your inbox