agents
Where does Cursor Remote Control run the agent loop?
Cursor's changelog says Remote Control keeps agents local, while its mobile docs say the agent loop is in the cloud and tools stay local.
Personal Agent Protocol is an OAuth session, but its v0.1 specification is not published
PAP uses one OAuth session across web, API, and company-agent routes, but its v0.1 specification and payment extensions are not published.
Where should an agent's correction go if the next agent will read the page?
Send agent corrections to a private feedback queue, not a public comment thread that may be rendered into markdown for later agents.
AI coding agent CLI pricing and usage limits, October 2026
Paid tiers start at ₹649/month in India or $10/month for Copilot Pro; heavy-use tiers reach $100–$500/month. Cursor publishes pools, not dollar allowances.
Git conflicts and dirty worktrees with AI coding agents: what Aider, Claude Code, and Codex actually do
Aider 0.86.2 commits dirty changes, Claude Code 2.1.292 snapshots files, and Codex CLI 0.160.1 isolates parallel work in Git worktrees.
Synara 1.0.0 moves Oh My Pi onto the stable app
Synara 1.0.0 puts Oh My Pi, Inbox, provider accounts, handoffs, and Auto-fix CI in Stable; Hubs and Tasks stay in Beta.
Devin stores what it learned in a git repo, then dreams on it
Devin stores cross-session memory in a Git repo with a MEMORY.md index, rejects stale concurrent writes, and runs a daily dreaming pass to consolidate notes.
How Cursor bills Auto after the split into Cost, Balance, and Intelligence
All Cursor Auto modes bill at the routed model's list price; eligible third-party routes add $0.25 per million tokens on Teams and Enterprise.
Lavish keeps the HTML and sends the pointing back to the agent
Lavish Editor pairs a local HTML file with a browser review UI, returning element and text annotations to a polling agent loop without cloud servers.
The /kun skill downloads its instructions from GitHub on every run
The /kun skill downloads a Node script from GitHub main on each invocation, caches root docs locally, then reads ENTRY.md to answer.
GitHub ReviewBench scores AI code review agents on 219 pull requests
GitHub ReviewBench compares AI code review agents on 219 pull requests with grounded and augmented precision, recall, and F1 metrics.
How pstack stacks agent-built pull requests with gh or Origin
pstack's autopilot-stack lets workers build PRs in parallel while one coordinator owns the linear stack, using gh or Origin without requiring Graphite.
Pi Durable checkpoints the turn, then resumes it
Pi Durable commits model and tool work to storage, then resumes unfinished tasks after a process restart.
LangGraph 1.2.13 keeps an old checkpoint update out of other branches
LangGraph 1.2.13 forks superseded checkpoints, isolates older update_state writes, preserves DeltaChannel counters, and filters answered get_state interrupts.
Cloudflare runs Pi inside a Durable Object, and the meter is wall-clock time
Cloudflare's PiHarness beta runs Pi Durable in a SQLite-backed Durable Object and meters its allocated 128 MB by wall-clock compute duration.
Cohere North 2 keeps agent memory and caps token spend
Cohere North 2 adds cross-session agent memory and North Admin flow control, with request and token-rate tiers for users and groups.
Instinct's group-chat agent works for people without an account
Instinct lets friends without accounts join a group agent, while personal agents ask before sharing data or pending replies.
Why robots.txt Cannot Stop Grok Bot
robots.txt cannot block Grok Bot's browser session; it can only guide crawlers that identify themselves and follow the Robots Exclusion Protocol.
How Meta Muse and Stripe Link handle autonomous purchases
Muse gets a user-approved Link spend request, then uses a one-time card or Link Pay Token while the agent never sees the user's real card details.
Rex public testing is a free macOS terminal with persistent sessions
On 2026-10-05 Rex opened macOS public testing as a free, self-hostable terminal with persistent sessions; Linux, Windows, and iOS are outside the test.