1,765 packages matching “glm-4v”
@bacnh85/pi-model-tools
v0.8.7 · 1 day ago
Unified tool-wrapping, argument repair, reasoning management, DeepSeek V4 guidance + Super Power Mode, defensive leak-cleaning, edit mismatch repair (read-notice stripping + trim-tolerant retry), and a Codex-style apply_patch diff tool for DeepSeek V4 and
No known vulnerabilities
pi-umans-provider
v1.0.27 · 13 hours ago
UMANS provider extension for pi - Access Kimi K2.6, GLM 5.1, Qwen 3.6, and coding-optimized models through the UMANS API
No known vulnerabilities
@kontourai/datum
v0.8.0 · 29 days ago
Portfolio AI provider/model registry: define providers, models, roles once; resolve which backend, which model, whose key, what base URL. Never makes model calls.
No known vulnerabilities
dsh-vision-proxy-route
v0.1.4 · 16 days ago
DeepSeek Harness plugin: a configurable provider route that transcribes pasted images via free Zhipu GLM vision models before delegating to a text-only adapter.
No known vulnerabilities
llm-cny
v1.0.45 · 3 months ago
在 OpenCode TUI 右侧栏显示多家 LLM 提供商的人民币费用、DeepSeek/moonshot China 余额和 Codex 限额。
No known vulnerabilities
pi-neuralwatt-provider
v1.18.24 · 13 hours ago
Neuralwatt provider extension for pi - Access Kimi, GLM, Qwen, GPT-OSS, Devstral, and MiniMax models through the Neuralwatt API
No known vulnerabilities
@estebanforge/pi-glm-tweaks
v1.7.1 · 14 days ago
Pi-native tweaks for Z.AI's GLM coding models (glm-5.2, glm-5.3, glm-5.3-flash, and [1m] variants). Restricts the Pi thinking-level UI to the modes each model supports on the wire, wires the native thinkingFormat:"zai" translation, and auto-clamps hidden
No known vulnerabilities
dsh-glm-vision
v1.0.3 · 22 days ago
GLM 视觉模型插件:注册 glm-vision 供应商路由(glm-4.6v 系列,image+text 输入声明)并提供 glm_vision 工具,让 DeepSeek 等文本主模型直接调用智谱视觉模型看图。
No known vulnerabilities
@jesonliu/image-recognition-mcp
v0.1.0 · 1 month ago
OpenAI-compatible vision recognition MCP server for Claude Code (and any MCP client).
No known vulnerabilities
dsh-quota-panel
v0.9.1 · 19 days ago
Provider quota/balance widget for the dsh web surface: collapsed glanceable capsule expanding into a Harness-native card with a settings panel (provider visibility / refresh interval / warn thresholds), fed by a loopback Connection RPC channel whose host
No known vulnerabilities
pi-coralbricks-provider
v1.0.16 · 11 hours ago
CoralBricks provider extension for pi - Access GLM 5.3, GLM 5.3 Flash, Kimi K3, and GPT-OSS 120B through the Coral Inference API
No known vulnerabilities
unqroute
v0.1.1 · 2 months ago
UnQRoute — Unified AI router with 160+ providers, RTK+Caveman compression, auto fallback, MCP/A2A, desktop, PWA, and OpenAI-compatible APIs. Forked from OmniRoute with Z.ai Web (GLM-5.2) integration.
No known vulnerabilities
@oflow-ai/oflow-cli
v0.2.8 · 6 months ago
oFlow CLI - AI-powered terminal assistant for developers
No known vulnerabilities
ghostycode
v0.0.23 · 19 days ago
Terminal coding agent for supported hosted and local models. One runtime on your machine. Rust, MIT.
No known vulnerabilities
pi-crof-provider
v1.0.24 · 2 days ago
CrofAI provider extension for pi - Access Kimi, GLM, Qwen, DeepSeek, MiniMax, and Gemma models through the CrofAI API
No known vulnerabilities
@glitterkill/glm-mcp-ultimate
v0.1.1 · 6 months ago
GLM MCP Ultimate - Allows Claude Code to delegate tasks to GLM (Zhipu AI) agents
No known vulnerabilities
pi-zhipu-usage
v0.2.0 · 1 month ago
Pi extension: show GLM Coding Plan usage and reset countdown in the footer. Supports Zhipu domestic (open.bigmodel.cn), international (api.z.ai), and local proxy / Headroom setups.
No known vulnerabilities
glm-vision
v1.4.3 · 1 month ago
Pi extension that gives non-vision GLM models (z.ai) image understanding via GLM-4.6V
No known vulnerabilities
pi-tensorix-provider
v1.0.18 · 13 hours ago
Tensorix provider extension for pi - Access DeepSeek, GLM, Kimi, Qwen, MiniMax, Llama, and more through the Tensorix API
No known vulnerabilities
command-code
v1.62.1 · 10 hours ago
Command Code, coding agent that continuously learns your coding taste. Best coding agent for open models.
No known vulnerabilities