AutoGLM (Zhipu AI)

https://xiao9905.github.io/AutoGLM/

Tsinghua spinout. Foundation agent series for autonomous smartphone/PC GUI control. Persistent task memory retains shopping history, app usage patterns, multi-step task state across sessions. AutoGLM-Thinking claimed first agent capable of concurrent thinking and acting.

Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 43 cited facts, 17 with a third-party source · 1 recorded change · Suggest a correction

At a glance

Tier
T2
Created
2025-12 vendor fix
Latest release
no releases fix
License
Apache-2.0 repo fix
Pricing
Free + paid third-party fix
Freshness
2026-10-22 fix
Layer
agent-infra repo fix
Licensing
open-source registry fix
Deployment locus
computer-use vendor fix
Platform vs product
both vendor fix
SDK languages
python repo fix

Memory taxonomy

storage
file
retrieval
injection
persistence
cross-session
update
extraction
unit
episode
governance
opaque
conflict
n/a

When to use

Optimised for: GUI agent + cross-session task memory

Anti-fit: searched not found

Pros & cons

Pros

Mobile / desktop autonomous agent with memory tuned for multi-step UI automation.

Cons

Closed product; primarily Chinese-market; documentation in Chinese.

Claims & capabilities

Supports 50+ high-frequency Chinese apps (WeChat, Taobao, Douyin, Meituan).

Technical surface

API surface
searched not found
Backend storage
searched not found
Deployment
Both
Embedding model
searched not found
Multi-tenancy
searched not found
MCP
not documented publicly
A2A
not documented publicly
OpenTelemetry
not documented publicly

Similar systems

Other dedicated memory layers in the catalog, ranked by inbound references.

  • Mem0 T1

    Universal memory layer for AI agents. Three concurrent stores (vector + graph + KV); LLM-extracted facts; concurrent retrieval via ThreadPoolExecutor.

  • Zep & Graphiti T1

    Bi-temporal knowledge graph (event time + ingestion time). Strong on chronological reasoning and contradiction tracking. Graphiti is the open-source core.

  • Cognee T1

    "Extract–Cognify–Load" pipeline that turns raw input into a typed, queryable knowledge graph for agent recall.

  • Hindsight (Vectorize) T1

    Standalone memory service from Vectorize. Open source. Biomimetic four-network design (World, Bank, Observation, Opinion). Ships an MCP memory server.

  • Letta / MemGPT T1

    Originated as MemGPT (UC Berkeley), where the model pages its own memory between context, recall and archival tiers. The product now centres on Letta Code, a stateful agent harness whose agents rewrite their own memory, skills and prompts over time.

  • Memori T2

    Structured, persistent memory layer for AI agents. Open source.

Sources (42 cited facts, 17 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-22
    • Funding / ownership “$400M $20.0B val Series D (approx) · 2024-05” → “public company — Zhipu AI IPO on HKEX (02513) 2026-01-08, ~HK$4.35B (~US$560M) gross proceeds at HK$116.20/share” source
    #195