Popular News
Latest News
Top Stories
View all
Obelisk 0.42 keeps agent progress in the database, not the process
From Mexico: Obelisk 0.42 (Oct 4) stores coding-agent workflow progress in a database, wraps generated code in nested server/app/deployment grants, and ships a workflow-agent prototype that can deploy and inspect apps after the process dies.
Cloudflare gives the agent a search box instead of a guessed URL
From Mexico: Cloudflare’s Oct 2 post puts web search on AI Gateway, so an agent can ask Ceramic, Exa, or Linkup instead of guessing a URL and curling a 404. Native server tools are still coming soon. The docs call it an open beta.
Supabase puts the backend in the repo the agent already edits
From Mexico: Supabase’s Oct 2 post moves schema and project config into the repo, runs a local stack without Docker, and lets an app ship its own MCP server. Compute, for long jobs, is still a private alpha.
Pi 1.0 keeps the coding agent small and finally takes MCP
From Mexico: Earendil shipped Pi 1.0 on Oct 1, a minimal coding-agent harness that adds MCP through Codemode, deferred tool loading, and virtual models. They kept the terminal agent small and put long runs in a separate experiment.
Sentry’s Seer Agent can change the project, one chat at a time
On September 29, Sentry’s Seer Agent can create dashboards, alerts, and triage inside a project, and it can read Datadog or Google Cloud while it diagnoses. The write permission does not outlive the chat.
Momentic’s Mo bug-bashes the app instead of leaving you a suite
Momentic launched Mo on September 28: give it a URL or a mobile build, and a swarm of agents bug-bashes the app. You get a report with recordings and repro steps. A lasting test suite is optional, and the beta counts are Momentic’s own.
Autoheal’s $7.9M seed targets the work after coding agents commit
Autoheal announced a $7.9M seed on Sep 28 for a self-improving software factory: shared context for post-coding agents, plus an evaluator and a healer that only land changes through a pull request you approve.
Cloudflare’s new cf CLI is built for coding agents first
Agents accounted for 48% of Wrangler usage last week, so Cloudflare rebuilt its CLI around them: JSON by default, natural-language command search, typed config, and an open-source generator called Forge behind it all.
Claude Code 2.1.283: audit your CLAUDE.md, pin your models
From Mexico: Claude Code 2.1.283, released Sep 25, adds /doctor prompt-audit to check your CLAUDE.md files, skills, agents, and commands for instructions written for older models, plus exact model pinning and a model deny list for admins. Here’s why I think instruction files deserve the same care as code.
Copilot Managed Runtime: Microsoft gives AI-built apps a governed home
From Mexico: on Sep 25 Microsoft put Copilot Managed Runtime into public preview, a tenant-hosted place to run apps built with Copilot Code, Cowork, Copilot Studio, or third-party tools, plus an SDK and CLI for developers. Here’s what it means for the dev teams who end up owning those apps.
