A new open-source project called 16agents lets AI coding agents take a 16-type personality test themselves and write their own report.html, scoring their self-described behavior against four hidden tr…
Supabase launched a BYO-MCP feature at its Select 2026 conference on October 2 that lets any Supabase app expose a Model Context Protocol server to users with a single command, npx shadcn@latest add @…
A developer outlined a blueprint for "Hermes," an operations copilot built on GitHub Copilot for a wood-interior design and fabrication studio, designed to convert customer inquiries into checked proj…
Developer JustasMonkev released lazy-clean, a standalone skill package for coding agents that injects a YAGNI-based "lazy-senior-dev" ruleset at session and subagent start and runs a heuristic slop ch…
A developer eliminated a recurring code-formatting friction point with their AI coding assistant by prepending the team's actual Black configuration — line-length 90, target-version py310, and skip-st…
Agent Plugins 1.0 packages MCP servers and Agent Skills into a single portable folder that works across ChatGPT, Codex, Cursor, GitHub Copilot, Kiro, and VS Code. The release targets developers who cu…
Twelve of the 13 AI coding agents reviewed on October 3, 2026 document a way to intercept a tool call before it runs, while Continue is the only one with no hook documentation, according to a survey o…
A developer released Agent Scrub, a macOS 14+ menu-bar tool that scans and redacts plaintext API keys, tokens, and other secrets stored in the local conversation history of AI coding agents including …
Agnostic-ai released v0.78.0, which extends `agnostic-ai hook run` to execute hooks as Crush, Cursor, Copilot, Factory, Qoder, and Antigravity would, counting assumed results only with `--include-assu…
A context engine operates as a five-stage pipeline — ingestion, graph construction, retrieval-and-reasoning, conflict resolution, and permissioned delivery — with the hard engineering in keeping all f…
GitHub made Copilot code review requestable through its REST and GraphQL APIs and set Balanced as the default review effort level, generally available to Copilot Pro, Pro+, Max, Business, and Enterpri…
GitHub deprecated four models across all GitHub Copilot experiences on October 2, 2026: Gemini 3.5 Flash, Gemini 3.6 Flash, Kimi K2.7 Code, and Claude Opus 4.7. GitHub recommends Gemini 3.8 Flash for …
Anthropic released Claude Code v2.1.287 on Thursday, adding mods — JavaScript or TypeScript event-handler plugins that can redraw the tool's interface or intercept a tool call before it runs, enabled …
GitGuardian has published a Docker Sandbox Mixin Kit that automatically installs its ggshield tool and enables AI hooks, giving developers a controlled way to run autonomous coding assistants. The kit…
A developer outlined four habits for using AI coding assistants like Copilot, Claude, and Cursor as thinking partners rather than code generators, including a 15-minute rule for debugging and a struct…
A developer's late September–early October 2026 survey of GPT and Anthropic models found subagent token usage runs 15–35% of a main agent session's usage, and recommends GPT-6 Luna (xhigh) for explore…
A developer argues that AI coding agents have shifted the bottleneck from code generation to context engineering, proposing that repositories expose project-level instruction files such as AGENTS.md, …
Microsoft released a public slice of GitHub Copilot coding-agent telemetry on October 1st, giving researchers 301,026 sessions covering 9.3 million LLM calls and 8.7 million tool calls, according to M…
Microsoft's official Playwright MCP server lets AI assistants such as Claude Code, GitHub Copilot and Cursor drive a real browser through structured accessibility snapshots rather than screenshots, so…
A new VSCode extension, "More Providers," lets GitHub Copilot Chat run models hosted on NEAR AI Cloud, which shields prompts, model weights, and outputs inside Trusted Execution Environments built on …