Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Introducing the Knowledge Base MCP. Greptile maintains a detailed knowledge base of how every part of your codebase works, as well as a history of past incidents. Starting today coding agents like Codex, Claude can access the Knowledge Base via Greptile's MCP, so they can use Greptile's learnings to...

64,850 Aufrufe • vor 9 Tagen •via X (Twitter)

22 Kommentare

Profilbild von Greptile
Greptilevor 9 Tagen

Learn more:

Profilbild von Simantak
Simantakvor 9 Tagen

Yalls dont stop shipping do you. Love it team

Profilbild von Max
Maxvor 9 Tagen

Greptile knowledge base is slept on. It's so powerful having all the context in one place & constantly evolving

Profilbild von Martin Jonsson
Martin Jonssonvor 9 Tagen

Does it work on historical? Lots of reviews behind me.

Profilbild von Saai Arora
Saai Aroravor 9 Tagen

Damnnn this is fire

Profilbild von Varik Verilion
Varik Verilionvor 9 Tagen

Incident history inside the coding loop is a useful addition.

Profilbild von EKOS _ AGI 🦊 🇮🇷
EKOS _ AGI 🦊 🇮🇷vor 8 Tagen

This is where agent memory starts becoming real infrastructure. The next challenge is making that accumulated knowledge structured, versioned, and traceable — so agents don’t just remember what happened, but understand how that knowledge evolved and where it came from.

Profilbild von Yijie
Yijievor 8 Tagen

production quality on this is crazy

Profilbild von cole murray
cole murrayvor 9 Tagen

awesome!

Profilbild von Samuel Hu
Samuel Huvor 9 Tagen

the history-of-incidents bit is what i actually want. most mcp demos can answer a file question, but the "why did we do this weird thing" context is the part i keep missing — does it update itself from prs or only docs?

Profilbild von Dominik
Dominikvor 9 Tagen

the useful boundary is not 'agent can read the codebase.' it is whether each retrieved fact carries provenance, freshness, and an owner. otherwise a knowledge base becomes another prompt-shaped authority with no way to tell stale guidance from a current constraint.

Profilbild von AWE
AWEvor 8 Tagen

does the incident history get pulled in automatically or does someone still have to write the postmortem

Profilbild von Ali Mirza | AI Agents & Automation
Ali Mirza | AI Agents & Automationvor 8 Tagen

hooking an mcp incident log directly into the subagent prompt stops it from making the same breaking imports twice.

Profilbild von Bessi
Bessivor 8 Tagen

past incidents in the MCP. did not expect that

Profilbild von virtualuncle
virtualunclevor 8 Tagen

most codebase context tools tell the agent how things work. knowing how it broke last time is a step past that

Profilbild von Mike Lopez
Mike Lopezvor 8 Tagen

How do you prevent stale architectural knowledge from becoming authoritative context for the agent?

Profilbild von Mohamed Khlifa
Mohamed Khlifavor 8 Tagen

What is the difference between it and things like onsidian git that is free and most common for users ?.

Profilbild von 0xdotdot
0xdotdotvor 8 Tagen

fire

Profilbild von Omair-Inam Abdul-Matin
Omair-Inam Abdul-Matinvor 8 Tagen

How much will this cost?

Profilbild von Jag
Jagvor 9 Tagen

Interesting. So all the code base replicates to greptile?

Profilbild von AI Mastery Guide
AI Mastery Guidevor 8 Tagen

past incidents remembered, that's smart

Profilbild von TonkaToyXL | AI Test Cabin
TonkaToyXL | AI Test Cabinvor 8 Tagen

This is the missing piece for coding agents. Giving them a living map of the codebase and past incidents is how they stop guessing and start helping for real.

Ähnliche Videos