Fresh stories
Devin adds persistent memory with overnight cleanup
Cognition’s Memory and Dreaming features build a memory graph across Devin sessions and revise stale records overnight. The open-source system is designed to work across harnesses and environments.
Era generates simulated companies for agent testing
Era generates connected Salesforce, Zendesk, Jira, Slack, and Gong data behind vendor-compatible interfaces. Teams can reset the company and rerun identical tasks without human operations.
SemiAnalysis reports 4–5× more API-equivalent value from Anthropic subscriptions
SemiAnalysis treats subscription plans as model-specific credits and reports 4–5× more API-equivalent value for Anthropic plans than OpenAI’s. Task-cost-adjusted comparisons still favor Claude by 1.3–2.9×.
Pi Durable persists agent state beyond the transcript
Pi Durable persists in-flight tools, application state, and subagents so long-running agents can suspend and resume across environments. Demonstrations show checkpointed memory, approvals, and desktop control across devices.
Devin adds persistent memory with overnight cleanup
Cognition’s Memory and Dreaming features build a memory graph across Devin sessions and revise stale records overnight. The open-source system is designed to work across harnesses and environments.
Epoch estimates OpenAI researchers’ coding-agent use doubled every 34 days
Epoch estimates coding-agent usage doubled every 34 days at the median and every 27 days at the 90th percentile from January through August. The figures use API prices rather than OpenAI’s actual costs.
gdp-ts makes authorization proofs compile-time requirements
The gdp-ts library, linter, and AI skill require typed proofs that authorization checks ran before sensitive calls. Its rules also flag forged proofs and unsafe escape hatches.
Era generates simulated companies for agent testing
ContextQA ships Ship to test deployed user flows
Reflection releases 501B-parameter Beam model
SemiAnalysis reports 4–5× more API-equivalent value from Anthropic subscriptions
Top storiesthis week
Claude Code Mods walkthrough says plugins run unsandboxed with user permissions
A Claude Code Mods walkthrough says plugins retain state and run with the user's permissions. Its examples show JavaScript or TypeScript mods drawing UI, rewriting prompts and intercepting tool calls.
Teknium says Hermes checks nearly 500 plugins for malware, not security hardening
Teknium says Hermes lists nearly 500 plugins, but only eight are officially tested. Community submissions get malware and guideline checks, not broader security hardening.
Geoffrey Huntley demos an SBCL kernel that modifies itself while running
Geoffrey Huntley's experimental SBCL kernel uses LLM tool calls to add functions, test them and hot-reload passing changes. It saves revisions with rollback support; a fresh process reproduced a successful revision.
Matt Pocock releases skills v1.3 with /retro transcript reviews
Matt Pocock's skills v1.3 adds /retro to find workflow improvements in old agent transcripts. Its migration prompt compares installed skills, renames CONTEXT.md to GLOSSARY.md and reviews recent skill usage.
Pi Durable agent resumes after redeploying itself with SQLite memory
Raunak demonstrates a Pi Durable agent that resumes after redeploying itself. Its Durable Object setup stores memory and chat history in SQLite, preserving both across deployments.