ContextCore: AI Agents conversations to an MCP-queryable memory layer
Hello :). This OSS product is for you (or future-you) who reached the point of wanting to tap into the ton of knowledge you have in your AI chat histories. "Hey, Agent, we have a problem with SomeClass.function, remind me what we changed in the past few months". Product's tl;dr: ContextCore is a local-first memory layer that ingests AI coding chats across multiple IDE assistants and machines, makes them searchable (keyword + optional semantic), and exposes them to assistants over MCP so future sessions don’t start from zero. IMPORTANT: I emphasize local-first, as in nothing is sent to any LLM other than when you explicitly use the MCP server in the context of using an LLM. However, once you engage semantic vector search OR chat content summarization, we DO use LLMs (although you can use lo
Hello :). This OSS product is for you (or future-you) who reached the point of wanting to tap into the ton of knowledge you have in your AI chat histories. "Hey, Agent, we have a problem with SomeClass.function, remind me what we changed in the past few months".
https://reach2.ai/context-core/
https://github.com/Kyliathy/context-core.git
Product's tl;dr:
ContextCore is a local-first memory layer that ingests AI coding chats across multiple IDE assistants and machines, makes them searchable (keyword + optional semantic), and exposes them to assistants over MCP so future sessions don’t start from zero.
IMPORTANT: I emphasize local-first, as in nothing is sent to any LLM other than when you explicitly use the MCP server in the context of using an LLM. However, once you engage semantic vector search OR chat content summarization, we DO use LLMs (although you can use local ones).
ContextCore is not just “chat history storage.” It is a developer-grade memory layer that turns AI-assisted development from ephemeral to iterative—where prior debugging sessions, architectural decisions, refactors, and tool-call outcomes become reusable context rather than lost effort.
More in the README.md in the repo.
This is the first time I show this in a public forum :). My hope is that I get a little bit of feedback, hopefully even traction, so that I can get some help to expand ContextCore's compatibility (to add parsers for IntelliJ or other IDEs for example - which is quite easy now that the project has solid architecure docs and templates). The project has a roadmap in the README.
The endgame for ContextCore is to become an engineer's reliable side-kick when it comes to digging into chat history and turning that into pure context gold at the MINIMUM amount of tokens spent. The current search system is decent, but much more can be done.
And my endgame is twofold: 1) give something back after being a lurker for years and 2) get some help to polish the search system and other areas of the product, so that we create an awesome, vendor-independent, cross-agent memory layer.
Thank you for reading this! :)
DEV Community
https://dev.to/kyliathy/contextcore-ai-agents-conversations-to-an-mcp-queryable-memory-layer-4h1pSign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
productassistantagent
3 AI tools that make keeping up with the news easier
This article is republished with permission from Wonder Tools , a newsletter that helps you discover the most useful sites and apps. I can’t keep up with all the news that interests me. So I’m exploring new ways to get concise, curated updates. Today I’m sharing three new tools I like. Huxe : Personalized audio shows drawn from your interests, calendar, and email. Google CC : A morning summary of your email inbox. Yutori Scouts : AI agents that monitor your fave topics and deliver reports. Read on for examples of how each works, and how to make the most of them. Huxe : Personalized Audio Updates Huxe is a personalized audio app. Whenever I open it, I hear a custom podcast it generates on the spot based on my interests, calendar, and email. It greets me with what’s important on my calendar
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Products
OpenAI buying TBPN makes little sense, par for the course for a company that, like Twitter, stumbled into a big market and may never build a functional business (Ben Thompson/Stratechery)
Ben Thompson / Stratechery : OpenAI buying TBPN makes little sense, par for the course for a company that, like Twitter, stumbled into a big market and may never build a functional business OpenAI's purchase of TBPN makes no sense, which may be par for the course for OpenAI. Then, AI is breaking stuff, starting with tech services.
Using AI to prepare and evaluate environmental assessments risks ‘robodebt-style’ failures, scientists say
Conservationists warn the move could push species closer to extinction and says clearer environmental rules are needed instead Get our breaking news email , free app or daily news podcast Conservationists and scientists have warned a mining lobby proposal to use artificial intelligence to speed up national environmental approvals could generate “Robodebt-style” failures, putting threatened species at further risk. The Minerals Council of Australia has asked the government to spend $13m to trial the use of AI to help companies prepare applications and help the federal government make decisions. Continue reading...
3 AI tools that make keeping up with the news easier
This article is republished with permission from Wonder Tools , a newsletter that helps you discover the most useful sites and apps. I can’t keep up with all the news that interests me. So I’m exploring new ways to get concise, curated updates. Today I’m sharing three new tools I like. Huxe : Personalized audio shows drawn from your interests, calendar, and email. Google CC : A morning summary of your email inbox. Yutori Scouts : AI agents that monitor your fave topics and deliver reports. Read on for examples of how each works, and how to make the most of them. Huxe : Personalized Audio Updates Huxe is a personalized audio app. Whenever I open it, I hear a custom podcast it generates on the spot based on my interests, calendar, and email. It greets me with what’s important on my calendar
I revived an 1820s sea shanty with AI, and it’s a banger
My kids have been really into sea shanties lately (my family has eclectic musical tastes.) There are a surprisingly large number of modern shanties on YouTube and TikTok . But one historic song, The Wellermen , really spoke to me. Going down a rabbit hole of the song’s history, I learned that it was written in 1966 by a New Zealander. But the whaling classic was inspired by a much older song from 1820. Eventually, I found the lyrics to the original. But there was a problem–the words were cryptic and the melody was lost to the sands of time, making it impossible to sing. So, I decided to leverage today’s most powerful music-generating AI to bring it back. The result is a modern shanty that draws word for word on the 19th century original. Spoiler alert: it’s a banger. Here’s how I made it–a
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!