Open-source context runtime and governance layer for coding agents. MCP server + Python SDK (Anthropic, LangChain, OpenAI Agents, Google ADK) with shared procedures, failure rescue, loop detection, cost tracking, and cross-vendor model routing across Claude Code, Codex, Copilot, opencode, and any MCP host.
View on GitHub →
Try with Claude — $10 free →
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Claude Desktop
Claude Code
Cursor
Add to claude_desktop_config.json:
{
"mcpServers": {
"atelier": {
"command": "uvx",
"args": [
"atelier"
]
}
}
}📋 Copy
Run in terminal:
claude mcp add atelier uvx atelier📋 Copy
Add to .cursor/mcp.json:
{
"mcpServers": {
"atelier": {
"command": "uvx",
"args": [
"atelier"
]
}
}
}📋 Copy
Or install with pip: pip install atelier
README Excerpt
<!-- cspell:ignore Alamofire Excalidraw ast-grep codegraph ctags django jcodemunch nohit okhttp scip serena tokio vscode zoekt --> Local-first MCP tools, agents, and skills that help coding agents spend less time rediscovering your repo. > Claude Code: ~52% cheaper · 79.8% fewer tokens · 80.9% fewer tool calls
Tools (5)
edit memory node read shell
Topics
agent-memory ai-agents claude-code cli codex coding-agents copilot developer-tools gemini langchain llm loop-detection mcp observability openai-agents-sdk