The Brains turns founders into cited MCPs.

// 1h agoOPENSOURCE RELEASE

The Brains turns founders into cited MCPs.

ANNOUNCEMENT PRODUCT GITHUB PRODUCT HUNT

The Brains packages 37 founders, CEOs, and investors into searchable MCP servers built from public talks, essays, interviews, and posts. It works with Claude, Cursor, ChatGPT, Codex, and other MCP clients, returning source-linked answers.

// ANALYSIS

The clever insight is treating influential people as queryable, source-grounded datasets rather than synthetic “personality” chatbots.

–MCP makes these curated knowledge bases usable inside existing developer workflows.
–Citations help separate documented opinions from model-generated speculation.
–The curated corpus is useful for founder research, pricing decisions, and product strategy.
–Unofficial coverage and changing viewpoints make source dates, completeness, and takedown processes essential.
–MIT licensing and self-hosting give developers a path to build their own specialized brains.

// TAGS

the-brainsmcpragsearchknowledge-graphopen-sourcedevtool

DISCOVERED

1h ago

2026-10-21

PUBLISHED

7h ago

2026-10-21

RELEVANCE

8/ 10

AUTHOR

Victor Giurgiu

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE11m ago

Motion Studio 2.2 Adds Reduced-Motion Support

Motion Studio 2.2 flags animations without reduced-motion alternatives, then lets developers create an accessible version manually or ask Ultramotion to generate one. The update builds accessibility checks directly into the animation authoring workflow.

LAUNCH43m ago

Raylight API Turns Feature Releases Into Videos

Raylight API turns briefs, screenshots, and release context into scripted feature videos through REST, TypeScript, CLI, GitHub Actions, or MCP. It drafts pitches for free, then renders an editable Raylight project after approval.

OPEN SOURCE48m ago

deepseek-recipe ships production prompt codecs

DeepSeek’s 0.2.0 release adds Rust libraries and Python bindings that normalize Messages, Chat Completions, and Responses requests, render V4/V4.1 prompts, tokenize them, and parse streamed outputs back into API responses. Explicit special-token ranges keep user-supplied control-token spellings as ordinary text, mitigating a subtle prompt-boundary risk. [GitHub](https://github.com/deepseek-ai/deepseek-recipe/blob/main/CHANGELOG.md)