Compresses AI chat sessions into a typed knowledge graph. Local/offline via Ollama.
Compresses AI chat sessions into a typed knowledge graph. Local/offline via Ollama.
Converts raw AI chat (40k+ tokens) into a compact typed knowledge graph (~300–800 tokens) and writes it to .github/copilot-instructions.md or CLAUDE.md — automatically included in every AI turn across all modes (ask, edit, agent). No MCP server required for the core workflow.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"fish-bridge": {
"command": "uvx",
"args": ["fish-bridge-mcp"],
"env": {
"FISH_BRIDGE_BACKEND": "your-value",
"GEMINI_API_KEY": "your-value",
"ANTHROPIC_API_KEY": "your-value",
"OPENAI_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| FISH_BRIDGE_BACKEND | Configuration value read at startup. | Optional |
| GEMINI_API_KEY | Credential the server authenticates with. | Yes |
| ANTHROPIC_API_KEY | Credential the server authenticates with. | Yes |
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Local-first memory for AI coding agents. Memory + CodeGraph + Wiki in one SQLite file.
Stateless agentic tools over MCP: concept extraction, long-context, knowledge graph, planning.
Self-hosted semantic memory over MCP for an engineering team's tacit knowledge. Needs Postgres.
The MCP MariaDB Server provides a Model Context Protocol (MCP) interface for managing and querying MariaDB databases, supporting both standard SQL operations and advanced vector/embedding-based…