Free
$0/mo
Limited context (discontinued)
Supermaven was an ultra-fast AI code completion tool with a 1-million-token context window, pioneering long-context autocomplete in 2024. In November 2024 it was acquired by Anysphere (Cursor) and in November 2025 the standalone service was sunset. Its technology — the fast, context-aware Tab completion model — lives on inside Cursor as the foundation of Cursor Tab.
+ Pros
- Pioneered 1-million-token context window for autocomplete — far larger than any competitor at launch
- Sub-100ms completion latency — fastest inline autocomplete available in 2024
- Multi-IDE: VS Code, JetBrains, and Neovim (plugins still maintained post-acquisition)
- Coding-style adaptation on Pro plan — completions improved over time to match individual developer patterns
- Technology lives on inside Cursor Tab — accessible to all Cursor users
− Cons
- ⚠️ Standalone service sunset November 2025 — no new development or signups
- Acquired by Anysphere — effectively Cursor-only going forward, with no vendor-neutral path
- Autocomplete-only — no chat, agent mode, or multi-file editing capabilities
- Historical product only — referenced for context; new users should use Cursor instead
Pricing
Pro
$10/mo
1M context, style adaptation (discontinued)
Team
$10/user/mo
Team billing (discontinued)
Supermaven launched in February 2024 as a standalone AI code completion tool, built by Jacob Jackson (previously of GitHub Copilot and OpenAI) with a singular focus: the fastest, most context-aware autocomplete available. Its core innovation was a 1-million-token context window — over 30× larger than competing tools at launch — enabling the model to read entire codebases and provide completions that understood project-wide structure, naming conventions, and patterns. On the Pro plan it also adapted to individual coding style over time.
In November 2024, Anysphere (the company behind Cursor) acquired Supermaven to integrate its long-context Tab technology into Cursor's editor. The acquisition was announced on November 11, 2024 by both teams, with the explicit goal of combining Cursor's VS Code-based editing environment with Supermaven's completion model to build a faster, more context-aware Cursor Tab. The standalone Supermaven plugins for VS Code, JetBrains, and Neovim were kept maintained and free inference was provided for existing users.
By November 2025, Supermaven announced the sunsetting of the standalone service. Free autocomplete inference for existing customers was maintained for the foreseeable future, but active development shifted entirely to Cursor. Users seeking the same capabilities are directed to Cursor, where the Supermaven team's long-context completion technology powers Cursor Tab — the inline autocomplete that became a signature feature of Cursor's rise to $1B+ ARR by late 2025. For developers committed to non-Cursor editors, the Neovim plugin community has noted Supermaven's absence and migrated to alternatives such as Continue or Copilot.
Features (Historical — Now in Cursor Tab)
• ⚠️ Standalone service sunset November 2025 — technology now in Cursor Tab
• 1-million-token context window: read entire large codebases for completions (Pro)
• Sub-100ms latency: fastest autocomplete benchmarks among AI coding tools in 2024
• Coding-style adaptation: learned and matched individual developer patterns (Pro)
• Multi-IDE: VS Code, JetBrains, Neovim (plugins still maintained, no new features)
• Supermaven Chat: GPT-4o / Claude 3.5 Sonnet with hotkey-driven diff application
• Error fix: one-click compiler diagnostic upload with code context
• Founded Feb 2024 by Jacob Jackson (ex-GitHub Copilot, ex-OpenAI)
• Acquired by Anysphere/Cursor, November 11, 2024 (undisclosed sum)
• Sunset: November 2025
Version History
Major release: new 'Babble' model (2.5x larger), 1M token context window (up from 300K), team billing, improved serving infrastructure.
Added in-editor chat interface with GPT-4o, Claude 3.5 Sonnet, GPT-4; hotkey-based diffs, apply changes, and error fixing via compiler diagnostics.
Introduced a free tier with access to recently opened files for context but without the 1M token context window.
Added support for all JetBrains IDEs (IntelliJ, PyCharm, WebStorm, CLion, etc.) with full feature parity.
First code completion tool with a 300,000-token context window, custom neural network architecture, trained on edit sequences.
Signature Snippet
Before sunset: install the Supermaven VS Code extension, write a function signature — Supermaven reads 1 million tokens of codebase context and completes multi-line blocks at sub-100ms latency, faster than any competing tool. Today: the same capability is available inside Cursor as Cursor Tab.More in this Space
Vix
Vix is a Go-native, open-source (AGPL-3.0) AI coding agent that slashes token costs by 40-50% using a stem agent architecture and Tree-sitter virtual filesystem. It rethinks the plan/execute loop — keeping LLM cache warm across Explore, Plan, and Execute phases — while shipping Programmable Workflows, Whiteboard Mode with voice AI, MCP server support, and a self-evolving agent that writes its own scheduled jobs and watchers.
Late — High-Leverage AI Agent Orchestration
Orchestrate an entire AI dev team on 5GB VRAM using ephemeral subagents, exact-match diffs, and a zero-dependency Go binary. Works with any OpenAI-compatible model — local or cloud.
Paca
Paca is a free, open-source, self-hosted Scrum board where AI agents work as equal teammates — assigned to sprints, picking up tasks, and collaborating on BDD specs alongside humans. Built as an alternative to Jira and Linear, it treats AI agents as first-class Scrum members.