Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Bifrost
Bifrost
ClawBench
ClawBench

activeloopai/hivemind

Hivemind turns your traces into reusable skills across agents

#AI memory
Visit GitHub
TypeScript
1.6k
135
9 contributors
Apache License 2.0
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

ClawBench

a benchmark for personal agents

Momentum

How fast activeloopai/hivemind is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Aug 26 – Oct 25, 2026

Stars +61 in 61 days

0510
7

Forks +26 in 61 days

024
4

Merged PRs 18 in 61 days

0246
5

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Aug 26Sep 3Sep 11Sep 19Sep 27Oct 5Oct 13Oct 21
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Wed, Aug 26, 2026+2+00
Thu, Aug 27, 2026+1+00
Fri, Aug 28, 2026+1+00
Sat, Aug 29, 2026+1+00
Sun, Aug 30, 2026+3+00
Mon, Aug 31, 2026+0+20
Tue, Sep 1, 2026+1+00
Wed, Sep 2, 2026+2+01
Thu, Sep 3, 2026+0+01
Fri, Sep 4, 2026+0+00
Sat, Sep 5, 2026+0+00
Sun, Sep 6, 2026+1+10
Mon, Sep 7, 2026+2+10
Tue, Sep 8, 2026+2+00
Wed, Sep 9, 2026+0+00
Thu, Sep 10, 2026+2+01
Fri, Sep 11, 2026+1+11
Sat, Sep 12, 2026+4+00
Sun, Sep 13, 2026+1+10
Mon, Sep 14, 2026+2+00
Tue, Sep 15, 2026+7+01
Wed, Sep 16, 2026+1+02
Thu, Sep 17, 2026+0+05
Fri, Sep 18, 2026+1+00
Sat, Sep 19, 2026+1+00
Sun, Sep 20, 2026+1+00
Mon, Sep 21, 2026+0+10
Tue, Sep 22, 2026+1+00
Wed, Sep 23, 2026+0+00
Thu, Sep 24, 2026+0+00
Fri, Sep 25, 2026+4+20
Sat, Sep 26, 2026+0+00
Sun, Sep 27, 2026+1+00
Mon, Sep 28, 2026+0+01
Tue, Sep 29, 2026+0+10
Wed, Sep 30, 2026+0+00
Thu, Oct 1, 2026+0+00
Fri, Oct 2, 2026+0+00
Sat, Oct 3, 2026+0+10
Sun, Oct 4, 2026+1+10
Mon, Oct 5, 2026+1+00
Tue, Oct 6, 2026+0+00
Wed, Oct 7, 2026+1+00
Thu, Oct 8, 2026+0+00
Fri, Oct 9, 2026+0+10
Sat, Oct 10, 2026+0+00
Sun, Oct 11, 2026+0+00
Mon, Oct 12, 2026+0+00
Tue, Oct 13, 2026+3+00
Wed, Oct 14, 2026+2+11
Thu, Oct 15, 2026+2+00
Fri, Oct 16, 2026+0+20
Sat, Oct 17, 2026+1+40
Sun, Oct 18, 2026+0+20
Mon, Oct 19, 2026+0+30
Tue, Oct 20, 2026+1+10
Wed, Oct 21, 2026+3+00
Thu, Oct 22, 2026+2+03
Fri, Oct 23, 2026+0+00
Sat, Oct 24, 2026+1+01
Sun, Oct 25, 2026+0+00
Total+61+2618
  • 1#1 on the list
  • 7Rank that day
  • Not trending
2

    • GitHub trending history

    Where the repository ranked on GitHub Trending, one dot for each day it was on a list

    Jun 10, 2026Best #12

    #1#5#10#15#20#25
    Top 10
    Jun 10, 2026Jun 12, 2026
    The left and right arrow keys step from day to day; Home and End go to the first and the last

    Mentions and achievements

    Where people are talking about activeloopai/hivemind, and every badge it has earned
    1. Aug 71 post

      • Agent memory isn't the missing layer anymore, plenty of frameworks already cover it. Hivemind is still worth watching because it pushes trace-to-skill propagation: one agent repeats a workflow, and…

        Read full on X, posted by @alindnbrg

        @alindnbrg · x.com

    2. 20 days earlier
    3. Jul 181 post

      • the fix: i staged the summaries i cared about outside the batch path and flushed them. recall then fired. semantic, injected, relevance score 0.68.

        Read full on X, posted by @sebuzdugan

        @sebuzdugan · x.com

    4. Jul 171 post

      • where it shines is memory-heavy work. i asked a fresh agent about a bug i fixed in a past session, no files open, and it pulled the exact function and commit from memory. that is real cross-session…

        Read full on X, posted by @sebuzdugan

        @sebuzdugan · x.com

    5. 24 days earlier
    6. Jun 231 post

      • 1/ snapotter-hq/SnapOtter: a self-hosted suite of 150+ tools for images, PDFs, video, audio and files. AI-powered and fully offline, so your data stays with you. ⭐1745

        Read full on X, posted by @maksdizzy

        @maksdizzy · x.com

    7. 13 days earlier
    8. Jun 101 post

      • [2/4] 💻 HuggingFace OBLITERATUS/Gemma-4-12B-OBLITERATED · 183♥ · 8106 dl

        Read full on X, posted by @ProbBrain

        @ProbBrain · x.com

    9. Jun 92 posts

      • Hivemind reports 25% cheaper LoCoMo runs than a no-memory baseline. Coding agents still waste context on old work. A migration pattern gets solved once, then another agent rediscovers it from…

        Read full on X, posted by @DanKornas

        @DanKornas · x.com

      • Hivemind crossed 500 stars on github. 🚀 and 2.7K weekly installs. 🌟Star us here

        Read full on X, posted by @activeloop

        @activeloop · x.com

    10. Jun 81 post

      • HOLY SH*T @ActiveLoop just killed siloed prompting. Imagine if Cursor, Hermes, and Codex operated from the exact same brain. Hivemind turns every successful trace your team creates into a permanent,…

        Read full on X, posted by @DataChaz

        @DataChaz · x.com

    11. 7 days earlier
    12. Jun 11 post

      • Most AI coding tools still have the same problem: they don’t compound. Claude learns one thing. Codex learns another. Cursor understands part of your repo. Then the next session starts and everyone…

        Read full on X, posted by @iHateModelsss

        @iHateModelsss · x.com

    13. May 291 post

      • Propagates learned skills across multiple AI coding agents

        Read full on X, posted by @tom_doerr

        @tom_doerr · x.com

    You might also like

    Repositories close to activeloopai/hivemind
    FeaturedAdvertise to 180K+ monthly visitors
    Bifrost

    Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

    ClawBench

    a benchmark for personal agents

    akitaonrails/ai-memory

    Rust

    Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

    13.3k1k

    Dicklesworthstone/cass_memory_system

    TypeScript

    Procedural memory for AI coding agents: transforms scattered session history into persistent, cross-agent memory so every agent learns from every other

    45163

    kitfunso/hippo-memory

    TypeScript

    Stop re-teaching your agent. Make your agent's memory work like a brain. Hippo is long-term memory for coding agents. It's a critical layer for your AI harness that connects across your different tools (Cursor, Claude Code, Codex). It keeps your proprietary data completely local, and it actually learns over time.

    78447

    hyperb1iss/sibyl

    Python

    Cross-agent memory for AI coding tools: one self-hostable knowledge graph shared by Claude Code, Codex, OpenCode, Cursor, and the agents you build.

    679

    legioncodeinc/honeycomb

    TypeScript

    AI coding agents forget. They forget across sessions, and they forget across tools. A decision you reached in Claude Code at midnight is invisible to Cursor the next morning. Honeycomb fixes that. Learn something once; recall it everywhere,

    11816

    Asymptote-Labs/agent-beacon

    Go

    The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu

    2.8k258

    mozilla-ai/cq

    Go

    An open standard for shared agent learning. Agents persist, share, and query collective knowledge so they stop rediscovering the same failures independently.

    1.3k75

    codejunkie99/agentic-stack

    Python

    One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge when you switch.

    2.3k301

    zilliztech/memsearch

    Python

    A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

    2.8k298