[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:hivemind":3},"\u003Ch1>\n  \u003Cbr \u002F>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Factiveloopai\u002Fhivemind\" rel=\"nofollow ugc noopener\">\n    \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Factiveloopai\u002Fhivemind\u002Fmain\u002Fdocs\u002Fpublic\u002Fhivemind-logo.svg\" alt=\"Hivemind\" width=\"120\" \u002F>\n  \u003C\u002Fa>\n  \u003Cbr \u002F>\n  Hivemind\n  \u003Cbr \u002F>\n\u003C\u002Fh1>\u003Ch4>One brain for all your agents\u003C\u002Fh4>\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@deeplake\u002Fhivemind\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002F@deeplake\u002Fhivemind?color=blue&label=npm&style=for-the-badge\" alt=\"npm\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Factiveloopai\u002Fhivemind\u002Fstargazers\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Factiveloopai\u002Fhivemind?style=for-the-badge&logo=github\" alt=\"GitHub stars\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Factiveloopai\u002Fhivemind\u002Fblob\u002FHEAD\u002FLICENSE\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-Apache%202.0-blue.svg?style=for-the-badge\" alt=\"License\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Factiveloopai\u002Fhivemind\u002Fblob\u002FHEAD\u002Fpackage.json\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fnode-%3E%3D22.0.0-brightgreen.svg?style=for-the-badge\" alt=\"Node\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fdeeplake.ai\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPowered%20by-Deeplake-orange.svg?style=for-the-badge\" alt=\"Deeplake\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.ycombinator.com\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FY%20Combinator-backed-ff6600.svg?style=for-the-badge\" alt=\"Y Combinator backed\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fjoin.slack.com\u002Ft\u002Fhubdb\u002Fshared_invite\u002Fzt-35zr0yil0-lnzJcQhACsBlB7~3lufrCg\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FSlack-chat-4A154B?logo=slack&logoColor=white&style=for-the-badge\" alt=\"Join us on Slack\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\u003Cp align=\"center\">\n  Auto-learning, cloud-backed shared brain for \u003Cb>Claude Code • OpenClaw • Codex • Cursor • Hermes • pi • Claude Cowork (Alpha)\u003C\u002Fb> agents.\u003Cbr \u002F>\n\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F28172\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Ftrendshift.io\u002Fapi\u002Fbadge\u002Frepositories\u002F28172\" alt=\"activeloopai\u002Fhivemind | Trendshift\" width=\"250\" height=\"55\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\u003Cblockquote>\n\u003Cp>One engineer's agent figures out a tricky migration on Monday.\u003C\u002Fp>\n\u003Cp>Tuesday, every agent on the team can execute the pattern.\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Cp>On \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.17753\" rel=\"nofollow ugc noopener\">LoCoMo\u003C\u002Fa>, the public long-context memory benchmark, Hivemind is \u003Cstrong>25% cheaper, 1.7× fewer tokens, and 31% fewer turns\u003C\u002Fstrong> than running without shared memory. (\u003Ca href=\"#benchmarks\" rel=\"nofollow ugc noopener\">See the numbers below.\u003C\u002Fa>)\u003C\u002Fp>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Factiveloopai\u002Fhivemind\u002Fmain\u002Fdocs\u002Fpublic\u002Fhivemind_cursor_readme_banner_dark.png\" alt=\"Cut Cursor spend by 34% with Hivemind\" width=\"100%\" \u002F>\n\u003C\u002Fp>\u003Cp>\u003Cstrong>Beyond memory.\u003C\u002Fstrong> Hivemind doesn't just remember. It mines your team's traces for repeated patterns and codifies them into reusable skills that propagate back into every agent on the team. The agent your junior engineer used this morning is sharper because of what your senior engineer's agent figured out last week.\u003C\u002Fp>\n\u003Cul>\n\u003Cli>📥 \u003Cstrong>Captures\u003C\u002Fstrong> every session's prompts, tool calls, and responses as structured traces in Deeplake\u003C\u002Fli>\n\u003Cli>🧠 \u003Cstrong>Codifies\u003C\u002Fstrong> patterns into reusable \u003Ccode>SKILL.md\u003C\u002Fcode> files, available to every agent on your team\u003C\u002Fli>\n\u003Cli>🔍 \u003Cstrong>Searches\u003C\u002Fstrong> traces and skills with hybrid lexical + semantic retrieval (BM25 fallback when embeddings off)\u003C\u002Fli>\n\u003Cli>🔗 \u003Cstrong>Propagates\u003C\u002Fstrong> capability across sessions, agents, teammates, and machines in real time\u003C\u002Fli>\n\u003Cli>📁 \u003Cstrong>Intercepts\u003C\u002Fstrong> file operations on \u003Ccode>~\u002F.deeplake\u002Fmemory\u002F\u003C\u002Fcode> through a virtual filesystem backed by SQL\u003C\u002Fli>\n\u003Cli>📝 \u003Cstrong>Summarizes\u003C\u002Fstrong> sessions into AI-generated wiki pages via a background worker at session end\u003C\u002Fli>\n\u003Cli>☁️ \u003Cstrong>BYOC\u003C\u002Fstrong>: keep data in your own GCS, Azure, S3, or on-prem bucket. \u003Ca href=\"#security--storage\" rel=\"nofollow ugc noopener\">See Security & storage\u003C\u002Fa>\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2>Benchmarks\u003C\u002Fh2>\n\u003Cp>On the \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.17753\" rel=\"nofollow ugc noopener\">LoCoMo\u003C\u002Fa> long-context memory benchmark (100 QA pairs, Claude Haiku via \u003Ccode>claude -p\u003C\u002Fcode>, hybrid lexical + semantic retrieval), Hivemind cuts cost, tokens, and turns versus a no-memory baseline:\u003C\u002Fp>\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>Metric\u003C\u002Fth>\n\u003Cth>Baseline\u003C\u002Fth>\n\u003Cth>Hivemind\u003C\u002Fth>\n\u003Cth>Improvement\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>Cost \u002F 100 QA\u003C\u002Ftd>\n\u003Ctd>$8.94\u003C\u002Ftd>\n\u003Ctd>$6.65\u003C\u002Ftd>\n\u003Ctd>\u003Cstrong>25% cheaper\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n",1784853422508]