# zai-org/GLM-5

GLM-5: From Vibe Coding to Agentic Engineering

Repository: https://github.com/zai-org/GLM-5
Canonical: https://ross.abutalabs.com/products/glm-5
Homepage: https://z.ai/blog/glm-5.2
License: Apache-2.0
License Family: permissive
Topics: agentic-ai, coding, llm, long-horizon
Last push: 2026-08-26T14:02:23+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 14
- inputs: {"age_days": 205, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7057, forks 911 (observed 2026-08-28T04:09:55.477483+00:00)

## What it is
GLM-5 is a family of open-weight large language models from Z.ai (Zhipu AI), including the flagship GLM-5.2 with 1M-token context and the multimodal, sparse-attention GLM-5.3-Flash (320B total / 18B active parameters). The repository provides model documentation, technical reports, benchmarks, and links to API services and hosted demos.

## Use cases
- run an open-source LLM for agentic coding tasks
- process very long documents with a 1M-token context model
- build AI agents that handle long-horizon engineering work
- serve a cost-efficient multimodal chat model locally
- compare open-weight models against Claude or Gemini on coding benchmarks
- integrate an LLM API into coding assistants and IDE tools

## When to choose
- you need a strong open-weight model for coding and agentic workflows
- your workload requires very long context (up to 1M tokens)
- you want multimodal understanding at low inference cost
- you need self-hostable models with an Apache-2.0 license

## When to avoid
- you need a small model that runs on consumer hardware without GPUs
- you only need embeddings or retrieval rather than a generative LLM
- you require fine-tuning tooling that this repo does not provide
- you need guaranteed SLA support from a commercial vendor

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, machine-learning, deep-learning, agent-framework, prompt-engineering
- domain: large-language-models, artificial-intelligence, developer-tools
- platform: python, cloud, self-hosted
- tags: open-weights, moe, long-context, multimodal, coding-llm, sparse-attention, speculative-decoding, chat-model, ai-agents, natural-language-processing, gpu

## Member repositories
- zai-org/GLM-5 (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:55.477483+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:40:29.871142+00:00, confidence not recorded.
  - readme: https://github.com/zai-org/GLM-5 (fetched 2026-08-28T04:09:55.477483+00:00, sha f6ac3642fd7c)
  - homepage: https://z.ai/blog/glm-5.2 (fetched 2026-08-29T08:36:25.127321+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.