THTutorHero

Everything / AI agents / Agent memory

Trend in AI agents · tag agent-memory · through Sep 2026

Agent memory Emerging

On TutorHero's Everything Index, Agent memory is emerging on GitHub: 0.76 of every 10,000 new public repos over the last three months (720 a month), 39x vs a year ago. The 12-month forecast says rising (+113%). By the end of 2032, lines in the same state ended between 0.01x and 2.5x of where they started (median 0.54x).

Per 10k new repos0.76720 new repos a month
Year over year39x3 months: +30%
Next 12 months+113%80% band +80% to 7x
2032, median of history0.54x90% of past cases: 0.01x to 2.5x
Attention2.24%of new stars, 8x in a year
Jev 2032 call0.78xBetter than most similar lines
Share on X

Since 2019, and the range to 2032

0.010.030.10.3131020192020202120222023202420252026202720282029203020312032Range to 2032 (history of similar lines)Stable Diffusion releasedChatGPT launchesGPT-4Llama 2, open weightsModel Context ProtocolDeepSeek-R1Claude Code previewHigh 1.89Jev 0.60Median 0.41Low 0.01

New repos per 10,000 (3-month average, log scale)12-month forecastRange to 2032: middle half and 90% of past similar linesJev's 2032 call

The range is not a forecast of this line: it is what GitHub lines in the same state (more than doubled its share of new repos in a year) did 1 to 5 years later, 2019 to 2026, applied to today's level. Past 5 years it is stretched, not measured. Checked out of time (learned before 2022, scored after), 71% of outcomes landed inside the 90% range, so read it as wide. Open it in the Everything chart.

Week by week

Last week431 new reposOct 12 to Oct 18 · +58% against the field
Last 4 weeks• -1%924 new repos, against the 4 weeks before and the field
AprMayJunJulAugSepOct

New public repos with the agent-memory tag each week (Monday to Sunday, UTC). The outlined bars, last week included, are still filling in, as tags are often added days after a repo is created, so their height will grow a little. "Against the field" divides the change by what the typical tag did, so a wave that lifts every tag does not count. Hover for the numbers.

Built vs talked about

Hacker News16 stories a month8x share of HN vs a year ago · titles with "agent memory"
Talk vs buildingTalk and building in stepHacker News 8x vs GitHub new repos 39x over the year, compared with the typical trend

Each line is its own share (of all new GitHub repos, all Hacker News stories, all English Wikipedia views, all new stars on the repos we track), shown as a share of its own peak, so the timing and shape compare even though the units differ. Hover for the counts. Tap a name to hide or show a line.

What it means

Studentslearning it, contributing, getting hiredCommit this year
  • Worth learning now: Agent memory is emerging, 39x share of new GitHub repos vs a year ago.
  • Start by reading deeplethe/utopia (+12.1k stars in 3 months) and bojieli/ai-agent-book (+8.4k stars in 3 months).
  • People to follow: BaiFu, Bojie Li, Volcengine.
  • Jev for someone who wants to contribute or get hired: Commit this year (2.8 of 4).
Founders and builderswhat to build nextCommit this year
  • Builders and attention both rising: new repos 39x, attention 8x in a year.
  • 20.9 new stars per new repo over 3 months, vs 8.50 for the typical trend: more demand per project than most fields.
  • The 12-month forecast for its share: +113% (Rising).
  • Talk and building in step: Hacker News 8x vs new repos 39x in a year, close to the typical trend.
  • Jev for a builder: Commit this year (2.6 of 4).
Investorswhich fields deserve research timeCommit this year
  • History: of past GitHub lines that more than doubled its share of new repos in a year, 61% had a smaller share 3 to 5 years later and 8% at least doubled.
  • Jev's 2032 call: better than most similar lines (unsure), which on the base rates means about 0.78x today's share by the end of 2032.
  • Attention: 2.24% of new stars on the repos we track, 8x in a year.
  • Hacker News: 16 stories a month, 8x share in a year.
  • Jev for an investor: Commit this year (2.6 of 4).
  • Not investment advice: this measures what people build on GitHub, not any company.
Developers choosing toolswhich tools to adoptTest small
  • Most-starred tools here lately: deeplethe/utopia (vouched), bojieli/ai-agent-book (vouched).
  • The field is emerging, so expect new tools and fast changes; pin versions.
  • Jev for a developer picking tools: Test small (2.4 of 4).

Repos carrying it now

deeplethe/utopiaWorld's first open-source enterprise world model.+12.1k stars in 3 months · vouchedbojieli/ai-agent-book《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码+8.4k stars in 3 months · vouchedvolcengine/OpenVikingSelf-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.+4.4k stars in 3 months · vouched666ghj/MiroFishA Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物+4.0k stars in 3 months · organictigerless-labs/agent-memoryLong-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage+2.9k stars in 3 months · new
semantica-agi/semanticaGraph-Native Infrastructure for Context and Accountable AI Systems+2.1k stars in 3 months · organic

People building it

BaiFuDo what you love, and love what you do.Influence 70Bojie LiAuthoring books on AI agents and infrastructure, plus networking tools.Influence 85VolcengineAI agent context, search, and distributed training tools.Influence 74xerj-orgCreating XERJ, an AI data search tool with autoindexing.Influence 69DeepLetheOpen-source AI research and products, including world models and agent tools.Influence 52Adrian Valeai-boostInfluence 63tigerless-labsOpen AI research lab shipping agent tools and experiments.Influence 59LettaBuilding stateful AI agents with persistent memory and learning.Influence 53

More in AI agents

AI agentsEmerging13x in a year · 17.3k new repos a monthAI agentEmerging13x in a year · 5.3k new repos a monthAgentic AIEmerging+296% in a year · 3.5k new repos a monthMulti-agent systemsEmerging13x in a year · 2.3k new repos a monthLangGraphEmerging+248% in a year · 1.8k new repos a monthLangChainCooling+27% in a year · 1.6k new repos a monthChatbotsCooling+12% in a year · 1.2k new repos a monthContext engineeringEmerging6x in a year · 508 new repos a monthAgent2Agent (A2A)Emerging4x in a year · 241 new repos a monthCrewAICooling+11% in a year · 150 new repos a monthDeep research agentsEmerging+241% in a year · 102 new repos a month

Questions

Is Agent memory growing on GitHub?

Yes. Its share of all new public GitHub repos is 39x vs a year ago and +30% over the last three months (Sep 2026). Phase: Emerging.

How many new Agent memory repos are created each month?

About 720 new public repos a month carry the agent-memory tag (three-month average to Sep 2026), or 0.76 of every 10,000 new repos.

What will Agent memory look like in 2032?

Nobody knows, and we say how much. Of past GitHub lines that more than doubled its share of new repos in a year, the middle half had between 0.14x and 1.27x of their share 3 to 5 years later, and 61% ended smaller. Jev's call: Better than most similar lines.

Is Agent memory more talked about than built?

Talk and building in step. Over the year its share of Hacker News stories moved 8x while its share of new GitHub repos moved 39x. New repos grew faster than talk for most AI trends this year, so the label compares it with the typical trend: about 1/1.4 of the talk per builder of the median trend.

Not investment advice. Measurements of what people build and star on GitHub, a statistical forecast, base rates and a model's reading of them. Nothing here is about any company's revenue, valuation or stock.