#developer-tools

Eight lanes of open-source AI agents mapped by licence, stars and commit activity, including which popular repos are not actually open source at all.

Whisper-family engines, VoiceInk and Handy against the subscription apps: what open-source dictation matches today, and where paid tools still earn the fee.

ChatGPT Voice arrived on Mac and Windows on July 23, 2026, wired into Codex and ChatGPT Work. The developer API is still signup-only, so this is app-only.

Anthropic's free Claude Code security plugin scans code as it's written across three layers, and a new on-demand deep-scan plugin backs it with real patches.

Cursor Router auto-classifies each coding request and picks the right model. Cursor claims up to 60% savings in A/B tests versus running everything on Opus.

An MCP spec is scheduled to finalize July 28 with a stateless core that drops sticky sessions. What the announced change breaks and where hosting gets cheaper.

SpaceXAI open-sourced Grok Build's Rust harness under Apache 2.0 days after a privacy scandal. Why a public repo is not the same as a security audit.

TypeScript 7.0's native compiler is stable a week after GA, but typescript-eslint, Vue, Svelte and Astro tooling are not. Who should migrate now.

Codex's MultiAgentV2 now encrypts what a parent agent tells its subagents, so developers lose the local audit trail. Why the July 15 disclosure matters.

Grok Build reportedly uploaded full repos and git history to xAI's cloud. The /privacy toggle never stopped it — a server-side flag did. Agent trust is infra.

Supabase will require TypeScript 5.0 across supabase-js and its bundled packages from 2027. A migration-readiness checklist for teams still on 4.x.

Cursor 3.11 adds durable parallel side chats, local search across your agent transcript history, and new cloud-agent hooks. What changes for teams.

Vercel adds tree and waterfall views to traces, exposing parent-child spans and parallel bottlenecks. A practical Next.js performance-debugging flow.

Claude Code's desktop app now ships an in-app sandboxed browser. What agent-driven browsing, OAuth testing, and UI checks mean for dev teams in 2026.

Apple's MLX framework explained for developers: unified-memory zero-copy ops, mlx-lm generation and LoRA fine-tuning, and why M5 beats llama.cpp on Mac.

Anthropic's Claude Code Artifacts turn a coding session into a private, live, shareable HTML page. What they are, the 16 MiB CSP limits, and team uses.

Cloudflare now lets AI agents deploy Workers instantly with no signup via temporary accounts. How the claim flow works, the limits, and when to use it in 2026.

Cursor, GitHub Copilot, and Devin Desktop all restructured pricing in June 2026. A seat-economics guide to credit caps, TCO, and which tool wins at your size.

Cursor Bugbot dropped from 5 minutes to 90 seconds via Composer 2.5, finding 10% more bugs at 22% lower cost. What the June 2026 update means for lean teams.

GitHub Copilot swapped flat request units for token-metered AI Credits on June 1, 2026. Power users report 10x-100x spikes. A 5-step spend audit to stay safe.

Gemini CLI stops serving Pro, Ultra, and free users on June 18, 2026. The 45-minute migration to Antigravity CLI, the silent failures, and the quota regression.

Cursor 3.7 Design Mode lets you point at elements, speak intent, and queue edits mid-run. Where multi-select and voice fit, and how to stop design-token drift.

GitHub's new desktop app turns Copilot into a control center for parallel agent sessions, each in an isolated worktree. Plus the GA Copilot SDK explained.

Cursor's new Organizations layer adds per-team budgets, model-tier segmentation, and SCIM Groups. How it compares to GitHub Copilot Enterprise governance.

Hands-on deep dive into LangChain 1.0 — agent protocol, LangGraph runtime, tool integrations, evals, and the migration path from 0.x to 1.0.

Migrate from the legacy TypeScript Codex CLI to the current Rust CLI — config.toml schema, auth surface, profile API, sandbox modes, rollout plan.

Five-way comparison — Claude Code, Cursor, Codex Desktop, Replit Agent 3, Devin. Pricing, agent autonomy, MCP, eval scores, and reference workloads.

Compare AI coding IDEs and agents by actual usage data. OpenClaw leads at 822B tokens/day. Developer workflows, pricing, and feature comparison.

Cursor 3 launches with the Agents Window for parallel agent orchestration, Composer 2, seamless cloud handoff, an integrated browser, and Marketplace plugins.

Developer guide to Perplexity's Agent API platform. Four APIs for search, agents, embeddings, and sandboxed code execution with enterprise controls.

AI coding assistant rankings for April 2026. Cursor Composer 2, GitHub Copilot, and Claude Code compared on features, benchmarks, pricing, and workflows.

Next.js 16.2 ships Agent DevTools for debugging AI integrations, Server Fast Refresh for instant code updates, and AI-ready project scaffolding.

March 2026 AI coding tool rankings: Claude Code leads satisfaction, Cursor hits $2B ARR, Copilot ships agentic features. Independent performance comparison.

GitHub Copilot integrates with Jira for AI-powered coding directly from project management tickets. Setup guide with model selection and workflow automation.

Windsurf replaces credits with quota-based pricing at $20, $40, and $200 tiers. Comparison with Cursor and Copilot pricing for AI coding tool budget planning.

Claude Code voice mode rolls out with push-to-talk and /voice command. New /batch and /simplify commands transform hands-free AI coding workflows.

Bloomberg reports Cursor AI reached $2B annual recurring revenue, doubling in 3 months. Enterprise adoption drives AI coding tool market leadership analysis.

Devin 2.2 adds desktop computer-use, self-reviewing PR code review, 3x faster startup, and Linear integration. Architecture, benchmarks, and setup guide.

Explore TypeScript 5.9 new features including improved type inference, decorator metadata, and performance enhancements. Migration tips and examples.

Claude Code, Aider, and Gemini CLI compared for terminal-based AI coding. Codebase awareness, git integration, and why the CLI renaissance is real.

Delegate coding tasks from Slack with Claude Code integration. End-to-end bug fixes, PR reviews. Complete enterprise workflow guide.

Master Cursor 2.0's agent-first architecture. Compare pricing ($20-200/mo), parallel agents, MCP integration, and Cursor vs Windsurf vs Copilot.

Master Cursor 2.1's clarifying questions and interactive plan UI. Better plan quality, searchable plans. Complete workflow guide.

Master Cursor's semantic search with 12.5% accuracy improvement. Instant grep, better code retention. Complete AI coding guide.

Use Gemini CLI with current Google free-tier limits, open-source caveats, MCP support, auth options, and safe production workflow guidance.