Pensieve

Purpose: Finding relevant code, files, and AI coding-agent context without repeated broad searches or excessive tool calls.

Inferred · not functionally tested

Audience: developers using AI coding agents

Inferred · not functionally tested

Functions: rag, data_extraction

Inferred · not functionally tested

Interfaces: API: unknown · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI, WEB · deployment: browser, cli, macos, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: tedhaley.ca · github.com. These links do not verify the individual claims.

In the RAG, search & retrieval space, Pensieve takes a focused approach. Inferred · not functionally tested: It focuses on finding relevant code, files, and AI coding-agent context without repeated broad searches or excessive tool calls. Inferred · not functionally tested: It is built as an open-source project for developers using AI coding agents. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: It runs on the web, the command line, and macOS, and it can be self-hosted.

Ted Haley builds and maintains Pensieve, and it first shipped in 2026. The project is developed in the open on GitHub with 62 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are Semantic Search, Exact Search, and Git Search. Basis unknown · not verified: Catalogued interfaces include an MCP server.

Summary written by a language model from the project’s public pages.