Skillget

context0

mcp
Guvenlik Denetimi
Basarisiz
Health Uyari
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 7 GitHub stars
Code Basarisiz
  • rm -rf — Recursive force deletion command in install.sh
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose

This tool saves your AI coding session progress and checkpoints, scoped to your current git repository and branch. It allows you to seamlessly resume exactly where you left off when switching between different AI coding tools or starting new sessions.

Security Assessment

Overall Risk: Medium. The tool is local-only, doesn't request dangerous system permissions, and contains no hardcoded secrets. However, there is a significant security flag in the installation process. The provided install script contains a recursive force deletion command (`rm -rf`). Piping a web script directly to your shell (`curl | sh`) always carries inherent risks, but the presence of aggressive deletion commands makes it potentially destructive if the script fails or behaves unexpectedly on your specific system. Beyond the installer, the application itself accesses your local file system and git data to read and save context files.

Quality Assessment

The project is very new and currently has extremely low visibility within the open-source community, evidenced by only having 7 GitHub stars. However, it is an actively maintained project with recent updates pushed just today. It is properly licensed under the standard MIT license, which is excellent for open-source transparency and legal clarity. Because it is written in Rust, the core application code is highly likely to be memory-safe and performant. Trust level for this tool is currently early-stage; it solves a specific developer pain point but lacks a large community to vouch for its long-term reliability.

Verdict

Use with caution due to aggressive deletion commands in the install script and the project's low community adoption.
SUMMARY

Save where you left off. Resume in any AI tool — context follows your git branch.

README.md

context0

Save where you left off. Resume in any AI tool — context follows your git branch.

Open Source · Free · No Signup · No Cloud · Local-only · MIT License

Screenshot 2026-02-25 at 2 12 27 AM

Why

AI coding sessions have no memory between tools. Tokens run out in Claude Code, you switch to Cursor, and you're back to re-explaining everything. context0 fixes that — it saves a checkpoint scoped to your git repo + branch so any tool can resume right where you left off.

Install

curl -fsSL https://raw.githubusercontent.com/SyedSibtainRazvi/context0/main/install.sh | sh

Works on macOS (Intel and Apple Silicon) and Linux (x86_64 and arm64).

Windows: download the .zip from Releases and add the binary to your PATH.

How it works (automatic with MCP)

With MCP configured, you don't run any commands. Just say "save context" or "I'm switching" and the agent saves everything. On the next session — in any tool — the agent loads it automatically.

Step 1 — install:

curl -fsSL https://raw.githubusercontent.com/SyedSibtainRazvi/context0/main/install.sh | sh

Step 2 — install rule files (once per project):

context0 init-rules

This tells the AI agent when and how to save/resume context. Writes CLAUDE.md, .cursor/rules/context0.mdc, and AGENTS.md into your project.

Step 3 — configure MCP for your tool:

Claude Code

claude mcp add context0 context0 mcp-server

Cursor

Cursor doesn't inherit your shell PATH — use the full binary path. Find it with which context0, then add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "context0": {
      "command": "/Users/your-username/.local/bin/context0",
      "args": ["mcp-server"]
    }
  }
}

Restart Cursor after editing.

Codex

Add to ~/.codex/config.json using the full path from which context0:

{
  "mcpServers": {
    "context0": {
      "command": "/Users/your-username/.local/bin/context0",
      "args": ["mcp-server"]
    }
  }
}

That's it. The agent handles everything from here. No commands to memorize.

CLI (optional, no MCP required)

Prefer to do it manually, or don't want MCP setup? The CLI works standalone:

# Save a checkpoint
context0 save \
  --done "implemented OAuth flow" \
  --next "add refresh token logic" \
  --files src/auth.rs --files src/middleware.rs

# Resume latest checkpoint
context0 resume

# Resume as JSON
context0 resume --json

# Show recent checkpoints
context0 log --limit 20

# Delete checkpoints for current branch
context0 clear

Docs

https://syedsibtainrazvi.github.io/context0

How context is scoped

  • Key is git repo root + branch — feature/auth and main stay completely separate
  • Stored in local SQLite at ~/.context0/context0.db — nothing leaves your machine
  • No cloud, no auth, no runtime dependencies

Storage

Setting Default
Database ~/.context0/context0.db
Override context0 --db /path/to/custom.db <command>
SQLite busy timeout 30000 ms (CONTEXT0_BUSY_TIMEOUT_MS)

Contributing

See CONTRIBUTING.md.

License

MIT

Yorumlar (0)

Sonuc bulunamadi