Developer & Code AI tools
46 tools featured in The Neuron newsletter.
- Agent Plugins
Packages your reusable Skills and MCP server configs once so compatible tools like ChatGPT, Codex, Cursor, and GitHub Copilot can load the same setup —free/open-source.
Details - Anthropic OSS Scanner
Scans enrolled open-source projects for vulnerabilities and suggests fixes.
Details - Atlaso
Construct turns repeatable work into scheduled agent workflows. BrowserOS Neo gives Claude, Codex, and Cursor a local browser. Atlaso shares one persistent memory across your AI tools. Xirp gives coding agents your company's real system context. Mem Agent tracks unfinished work and follows up automatically.
Details - Atomic
Turns natural-language engineering processes into verifiable coding-agent workflows with tests, repair loops, evidence, and human approval gates, so you can delegate longer coding jobs without babysitting every step (learn more in our stream w/ Alex from below).
Details - BrowserOS Neo
Construct turns repeatable work into scheduled agent workflows. BrowserOS Neo gives Claude, Codex, and Cursor a local browser. Atlaso shares one persistent memory across your AI tools. Xirp gives coding agents your company's real system context. Mem Agent tracks unfinished work and follows up automatically.
Details - Browzer
Reads your GitHub repo and drafts demos, changelogs, launch posts, cookbooks, and docs that can update as the code changes.
Details - Claude Code cloud sessions
Let coding jobs keep running on Anthropic's machines after your laptop closes.
Details - Claude in Chrome
Now turns the browser side panel into a Cowork session that keeps history, Skills, connectors, and multi-step tasks synced across Chrome and Claude’s apps.
Details - Claude Opus 5
Tackles difficult coding, research, legal, finance, and agent work near Fable 5 performance at roughly half the cost per task — paid, $5/M input and $25/M output tokens.
Details - Claude Opus 5.5
Cut Anthropic's frontier pricing while pushing harder on coding and agent work.
Details - Claude Sonnet 5.5
Tackles coding tasks with faster responses and fewer tokens, according to Anthropic.
Details - code
This is so cool (code); this type of use-case is what I mean when I say all computers should work like this in five years, locally; the computer should just be so much easier to use than it is today
Details - Codex Router
Runs multiple models side by side inside Codex without replacing official integrations (free and open source).
Details - companion guide
It covers second-brain files, CLAUDE.md, Skills, and four proactive Claude Cowork / Code levels. Watch it with our companion guide.
Details - Construct
Turns repeatable work into scheduled agent workflows. BrowserOS Neo gives Claude, Codex, and Cursor a local browser. Atlaso shares one persistent memory across your AI tools. Xirp gives coding agents your company's real system context. Mem Agent tracks unfinished work and follows up automatically.
Details - Cursor Projects
Keeps one coordinator on long-running coding work, then can monitor pull requests, Slack bugs, and scheduled maintenance after the first task ships.
Details - Cursor Router
Sends each coding request to the best-fit model, with Cost, Balance, and Intelligence modes and up to 60% savings in Cursor’s tests (Teams from $40/user/mo).
Details - Cursor’s Google Workspace plugins
Let your coding agent act across Gmail, Drive, Calendar, Docs, Sheets, and Chat through MCP; free, then $20/mo.
Details - DeerFlow 2.0
Gives you a local multi-agent workspace with memory, sandboxing, MCP, research, coding, and slides; free/open-source (model costs extra).
Details - Durable Actors
Gives developers persistent actors with their own SQLite state.
Details - ElevenLabs Hosted MCP
Removes the annoying local-server/API-key setup so Claude, Cursor, and other MCP clients can reach ElevenLabs through OAuth.
Details - Fugu-Ultra v1.1
Coordinates multiple frontier models for harder coding, reasoning, and agent tasks, with gains up to 7.9 benchmark points at the same price — paid, from $20/mo.
Details - Google's Gemini work agent
Plans tasks, delegates work, and can route them across agents.
Details - Grok Bot
Gives you always-on agents with persistent cloud computers that work across apps and coordinate with other bots —pricing not public.
Details - Gumloop
Lets your team build shared agents that automate tasks across Slack, Gmail, Salesforce, and other work apps while IT controls access, models, and spending (raised $50M) —14-day free trial, then $37/mo.
Details - Infisical
Lets you sandbox Claude or another agent behind a fake API key while its proxy swaps in the real credential only when requests leave the agent.
Details - InstaCloud
Gives coding agents serverless compute, Postgres, branching environments, and deploys they can operate end to end through CLI and skills.
Details - Mem Agent
Construct turns repeatable work into scheduled agent workflows. BrowserOS Neo gives Claude, Codex, and Cursor a local browser. Atlaso shares one persistent memory across your AI tools. Xirp gives coding agents your company's real system context. Mem Agent tracks unfinished work and follows up automatically.
Details - Meta Muse Code
Terminal agent with persistent background workers, repo-scale/multimodal execution, and verification.
Details - Meta’s models
Achieved gold-level results across five international STEM Olympiads, including perfect scores in two physics competitions using multi-agent reasoning without tools.
Details - Mistral Large 4
Gives you a frontier-class multimodal model across 160+ languages, with downloadable weights due by the end of October for teams that want to run or tune it themselves. Viva la French AI!
Details - Monid
Gives agents one pay-per-call gateway to 1,700+ tools and APIs instead of making you wire every service by hand.
Details - Muse for Small Business
Works across connected business apps in the background, asking for approval before sending, publishing, or spending.
Details - Muse Spark Open
Offers developers a downloadable model for coding agents, with commercial-use restrictions worth reviewing.
Details - NVIDIA PAIR
Spreads separate local-AI jobs across compatible computers on your network, so spare machines can work like a tiny home cluster.
Details - OpenResearch
Turns coding agents into experiment runners with isolated git worktrees and an immutable experiment tree.
Details - Opus 5 Skills Upgrade Prompt
Audits, rewrites, and blind-tests Claude Code skills —free to try.
Details - Perplexity Personal Computer
Puts its Computer agent on Windows 10/11 so it can work across your local files, Microsoft 365, and the web from one place.
Details - Perplexity’s remote MCP server
Use Perplexity’s remote MCP server to connect Claude Code, Cursor, or VS Code to its search, research, and reasoning tools without a local install (requires an API key; no separate MCP pricing announced).
Details - Rill Browser
Hands the webpage you’re viewing directly to Claude Code or Codex, so your coding agent gets the context without a copy-paste relay race.
Details - Siri AI
Is finally something you can try: the English beta adds personal context, onscreen awareness, web knowledge, and more actions across apps on supported devices.
Details - Vercel Agent Plugins
Portable Skills, MCP, hooks for ChatGPT / Codex, Cursor, Copilot, Kiro, VS Code.
Details - Warp Factory Benchmarks
Reruns your company’s real coding tasks across models so you can compare cost and quality on actual work.
Details - Watch it
It covers second-brain files, CLAUDE.md, Skills, and four proactive Claude Cowork / Code levels. Watch it with our companion guide.
Details - Watcher
Monitors Claude Code and Codex in real time, blocks dangerous commands before they run, and gives your team a security trail for every session —pricing not public.
Details - Xirp
Construct turns repeatable work into scheduled agent workflows. BrowserOS Neo gives Claude, Codex, and Cursor a local browser. Atlaso shares one persistent memory across your AI tools. Xirp gives coding agents your company's real system context. Mem Agent tracks unfinished work and follows up automatically.
Details