This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Open Agentic Brain & Memory (OpenAB)
Shared memory for AI coding tools that saves your tokens
Open-source, self-hosted long-term memory shared by AI coding agents: Claude Code, Codex, Cursor, Antigravity CLI and Kilo Code. Captures decisions across sessions and tools, stores them encrypted on your machine and in your own private GitHub, and brings back only what is relevant, and helps saved
I'm excited to launch Open Agentic Brain & Memory (OpenAB), an open-source shared memory for all your AI coding tools.
I use Claude Code, Cursor and Codex on the same projects every day. Each one starts blank, so I kept re-explaining my project and burning tokens and plan limits. So we built one memory they all share.
It's open source, so you can run it locally, own your data, or build the feature you want.
% Saves tokens: loading context for a 10,000-memory store takes 1,325 tokens instead of 1,131,367
T 18% of the tokens, 97% of the answers: on LocoMo it scores 86.6 vs 89.3 for reading the whole conversation (3.7k vs 20.8k tokens per question
* One tool learns it, every other tool knows it: each session starts with a briefing under 2,000 tokens
‹ Briefing ready in 84 ms, recall over 10,000 memories in 28 ms (p50)
* Works with 7 tools + any MCP client: Claude Code, Cursor, Codex, Antigravity, Kilo Code, Claude Desktop, ChatGPT desktop
• Doesn't start empty: learns from your existing projects on install
J Learns every day while you sleep, lessons wait for your approval @ Local, encrypted, synced to your own private GitHub. O accounts, Ø servers of ours
Syncs your skills across tools and machines
macOS and Linux • Free • Apache-2.0
Would love your feedback: how many tokens does your first day save you?
No comment highlights available yet. Please check back later!
About Open Agentic Brain & Memory (OpenAB) on Product Hunt
“Shared memory for AI coding tools that saves your tokens”
Open Agentic Brain & Memory (OpenAB) was submitted on Product Hunt and earned 2 upvotes and 1 comments, placing #152 on the daily leaderboard. Open-source, self-hosted long-term memory shared by AI coding agents: Claude Code, Codex, Cursor, Antigravity CLI and Kilo Code. Captures decisions across sessions and tools, stores them encrypted on your machine and in your own private GitHub, and brings back only what is relevant, and helps saved
Open Agentic Brain & Memory (OpenAB) was featured in Open Source (69k followers), Developer Tools (521.5k followers), Artificial Intelligence (481.6k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 269.8k products, making this a competitive space to launch in.
Who hunted Open Agentic Brain & Memory (OpenAB)?
Open Agentic Brain & Memory (OpenAB) was hunted by rohith hn. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Open Agentic Brain & Memory (OpenAB) stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
rohith hn
Hey Hunters
I'm excited to launch Open Agentic Brain & Memory (OpenAB), an open-source shared memory for all your AI coding tools.
I use Claude Code, Cursor and Codex on the same projects every day. Each one starts blank, so I kept re-explaining my project and burning tokens and plan limits. So we built one memory they all share.
It's open source, so you can run it locally, own your data, or build the feature you want.
% Saves tokens: loading context for a 10,000-memory store takes 1,325 tokens instead of 1,131,367
T 18% of the tokens, 97% of the answers: on LocoMo it scores 86.6 vs 89.3 for reading the whole conversation (3.7k vs 20.8k tokens per question
* One tool learns it, every other tool knows it: each session starts with a briefing under 2,000 tokens
‹ Briefing ready in 84 ms, recall over 10,000 memories in 28 ms (p50)
* Works with 7 tools + any MCP client: Claude Code, Cursor, Codex, Antigravity, Kilo Code, Claude Desktop, ChatGPT desktop
• Doesn't start empty: learns from your existing projects on install
J Learns every day while you sleep, lessons wait for your approval @ Local, encrypted, synced to your own private GitHub. O accounts, Ø servers of ours
Syncs your skills across tools and machines
macOS and Linux • Free • Apache-2.0
Would love your feedback: how many tokens does your first day save you?