shadowgraph
Local-first decision memory for AI agents — records what was chosen, what was rejected, why, and when to reconsider. MCP, CLI, and HTTP. Zero runtime dependencies.
No README could be loaded. View the project on GitHub for full documentation.
Frequently asked questions
What is shadowgraph?
shadowgraph is Local-first decision memory for AI agents — records what was chosen, what was rejected, why, and when to reconsider. MCP, CLI, and HTTP. Zero runtime dependencies.
How do I install shadowgraph?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is shadowgraph open source?
Yes — it is hosted on GitHub at https://github.com/LiLara-AI/shadowgraph and has 1 stars.
Related MCP tools
wigoloThe go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
iweMarkdown knowledge graph — LSP for your editor, CLI + MCP memory for your AI agents
projectmemOpen-source coding agent memory. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.
memoraGive your AI agents persistent, collective memory — with deduplicating absorb, supersession lineage, semantic search, and a graph UI. Speaks MCP.
atlassian-mcp-serverOfficial remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucket, and Compass to Claude, ChatGPT, Cursor, VS Code, and other AI tools using OAuth 2.1 or API tokens.
firecrawl-mcp-server🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP