Pretensor

- Data analysts using AI to explore warehouses.
- Data engineers tired of copy-pasting DDLs into chat.
- Data architects who need grounded schema context for agents.
- Anyone feeding database schemas to an LLM by hand.

pretensor index postgresql://USER:PASSWORD@HOST:5432/DBNAME pretensor serve --config-only # prints mcpServers JSON for Claude / Cursor

serve --config-onlyprints themcpServersJSONto stdout. Merge thepretensorentry into your Claude or Cursor MCP settings — the IDE starts the server automatically. Runpretensor servedirectly if you prefer a long-running terminal process (config hints go to stderr, keeping stdout clean for JSON-RPC).

Use--state-dironindex/reindexand--graph-dironservewhen overriding the default state directory (.pretensor).

pretensor analyze path/to/service-repo --connection mydb

analyzescans a repository for SQL string literals in Python source (stdlib AST — no code is executed), resolves each statement's table references with sqlglot, and links the issuing code to the matching tables in the graph as external consumers: service, file, line range, read/write op, and a confidence score. Raw SQL text is never stored, only a fingerprint. The results power theconsumersMCP tool and enrichimpact, so an agent can answer "which services consume this table?" with provenance.

Useful flags:--servicelabels the scanned repo (defaults to the directory name),--default-schemasets the schema assumed for unqualified table names,--dry-runpreviews without writing,--jsonemits a machine-readable summary. A# noqa: pretensor-analyzecomment on or above a statement opts it out.

Agents that don't run over MCP can still reach the graph tools. Pretensor exposesschema,context,traverse,impact,query, andvalidate_sqlas native tool objects for LangChain, LlamaIndex, and Google ADK — no MCP server process required. The adapters call the same underlying functions the MCP server uses, so output is identical.

from pathlib import Path from pretensor.integrations import load_langchain_tools # or load_llamaindex_tools, load_adk_tools tools = load_langchain_tools(Path(".pretensor"))

make test # pytest make lint # ruff check make typecheck # pyright

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Authenticated MCP and agent gateway for Forge Cascade private AI memory, provenance, graph search, and capsule lineage.

Local-first RLHF feedback loop for AI agents — capture preference signals, promote memories, block repeated mistakes, export DPO/KTO training pairs

Smriti is a Model Context Protocol (MCP) server that provides persistent, graph-based memory for LLM applications. Built on LadybugDB (embedded property graph database), it uses EcphoryRAG-inspired multi-stage retrieval - combining cue extraction, graph traversal, vector similarity, and multi-hop association - to deliver human-like memory recall.

A server for Zero-Vector's hybrid vector-graph persona and memory management system, featuring advanced LangGraph workflow capabilities.

Adaptive MCP memory system for AI applications. Learns which retrieval strategies work for your data, scores results using cognitive science models, builds a knowledge graph automatically, and validates every parameter change against real query history before adopting it. Patent pending.

Persistent memory for AI agents. Single SQLite file, 192 MCP tools. FTS5 search, knowledge graph, session handoffs, write gate. No server, no API keys, no LLM calls.

Multimodal RAG for source-backed AI answers

Corpus search and linguistic analysis for AI Agents

Highly efficient context management for agentic AI: MCP code search, evidence packs, graph context, and memory for large projects.