JSPM

n8n community node: DeepSeek R1/Reasoner Chat Model with proper reasoning_content handling for tool calls. Fixes the 'Missing reasoning_content field' error when using AI Agent with tools. Connect this as the Chat Model sub-node to your AI Agent.

Route Recoder CLI requests to different LLM providers including Kimi K2, Qwen 3, and DeepSeek R1

MCP server implementation for Deepseek R1 model

8 skills de ingeniería senior + 4 skills de diseño y creativas para DeepSeek R1. Protocolo de activación selectiva que maximiza el rendimiento del modelo sin saturar el contexto.

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

Tree-shakeable static models.dev catalog split by provider for TokenLens.

A powerful library for interacting with the Herc.ai API

A lightweight registry of LLM model information, like name and context sizes, for building AI-powered apps.

Information on LLM models, context window token limit, output token limit, pricing and more

Sapni — Self-Evolving AI Terminal Assistant

Cost calculator for Vercel AI SDK token usage. Supports OpenAI, Anthropic, Google, xAI (Grok), and DeepSeek with long context pricing, prompt caching, and reasoning tokens.

Local AI assistant: 80 tools (Gmail, Calendar, Drive, GitHub, Slack, browser, code, files), 38 agents, visual workflows (Studio, AWF, WebCraft). Install with `npm i -g nothumanallowed`, run with `nha ui`. Free tier built-in (Liara), no API key required. Y

Kepler — AI coding agent with operating brief, preflight planning, and sub-agents. SWE-bench Lite evaluated.

CLI tool for code analysis and generation using DeepSeek API

Switch between model providers (DeepSeek, Gemini, OpenAI, Anthropic) in Claude Code

MCP Server for DeepSeek API integration - enables Claude Code to use DeepSeek Chat and Reasoner models

OpenClaude opens coding-agent workflows to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

Cache-first DeepSeek coding agent for the terminal.

Generate AI summaries of test results using a wide range of AI models like OpenAI, Anthropic, Gemini, Mistral, Grok, DeepSeek, Azure, Perplexity, OpenRouter, and custom OpenAI-compatible APIs

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

Universal AI Development Platform with working MCP integration, multi-provider support, voice (TTS/STT/realtime), and professional CLI. 58+ external MCP servers discoverable, multimodal file processing, RAG pipelines. Build, test, and deploy AI applicatio

Minimal zero-dependency proxy from Anthropic Messages API to DeepSeek

Fast, minimal Node.js wrapper for the Voids API AI chat completions.

Install and run CodeWhale, the agentic terminal for open-source and open-weight coding models, from GitHub release artifacts.

🦾 MONSTER ENGINEER v2 - Ultimate AI CLI with 63 Skills, 12 Superpowers, 14 Agents. Multi-Agent Orchestration, Cost-Aware, Security Scorecard, Parallel-First.

Universal AI Terminal CLI — Ollama, Groq, OpenRouter, Google, Kimi, MiniMax, DeepSeek in one terminal

IO Intelligence provider extension for pi - Access DeepSeek, Kimi, GLM, Llama, Qwen, Mistral, and more through the IO Intelligence API

Autonomous coding agent CLI. Supports 8 providers: Groq, Gemini, Claude, DeepSeek, OpenAI, Mistral, xAI Grok, OpenRouter. Understands codebases, writes files, runs commands, searches the web.

A robust utility to repair JSON strings - fix malformed or broken JSON, especially from LLM output like ChatGPT.

Fine-tune cheap open-source LLMs (GLM, Qwen, DeepSeek) on your AI coding agent's successful runs with LoRA (SFT + DPO) so your model cascade escalates to expensive frontier models (GPT, Claude) less often — cutting cost-per-resolved. Turns run history int

n8n community node for DeepSeek V4 models (deepseek-v4-flash, deepseek-v4-pro) with thinking mode control

DeepSeek MCP Server - Model Context Protocol server for DeepSeek API

Connect local AI coding agents (Claude, Codex, Gemini, Qwen, DeepSeek, Cursor, OpenCode, Pi, OpenHuman, Reasonix) to the Grix scheduling platform. Also serves as an OpenClaw plugin for Grix channel transport.

LLM provider abstraction layer with unified streaming interface

Simple api for accessing deepseek free api

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

AI-powered coding assistant CLI using DeepSeek models

A Reactive CLI that generates commit messages for Git and Jujutsu with various AI

A CLI tool for DeepSeek AI

Cross-platform REPL-style AI CLI with multi-provider support

WormXGPT — Unfiltered Chaos CLI. Multi-provider AI chat with 100+ tools, MCP integration, auto-fallback, multi-agent orchestration. No filters, no limits.

n8n ChatModel node with extended reasoning/thinking support for OpenRouter, DeepSeek, and any OpenAI-compatible API

KOB CLI v2 - a beautiful, fully agentic AI coding assistant for your terminal. Made in Thailand.

Agents framework for Deepseek

Mesh terminal agent CLI — token-efficient coding agent with a shared LLM gateway.

Claude Code–class Ink TUI agent for DeepSeek v4 Pro (max thought, ultracode always on). Live follow-up queue, Shift+Tab permission modes, colored diffs, adversarial verifier — your keys, no login. Independent; inspired by Project Glasswing.

Pi coding agent extension to optimize DeepSeek models (official & third-party) by stripping thinking history, repairing tool pairings, and enforcing prompt caching.

oh-my-deepseek (omd) — Multi-agent orchestration layer for DeepSeek with prompt caching optimization.

Compatibility and diagnostics for DeepSeek V4 tool-calling agents.

Genkit plugin for DeepSeek API integration

DeepSeek adapter for rot-balance AI engine

A DeepSeek-native AI coding agent for your terminal

Pi extension for monitoring DeepSeek API balance

DeepSeek provider integration for Kortyx.

> 🚀 React Markdown 打字动画组件，提供现代聊天界面效果

RouterArena #1 among known public baselines: 96.77% accuracy, $0.0768/1K, 1.0000 robustness. OpenAI-compatible LLM router across 47+ providers.

Find the fastest coding LLM models in seconds — ping free models from multiple providers, pick the best one for OpenCode, Cursor, or any AI coding assistant.

Terminal AI coding agent for real repository work, powered by the DeepSeek API

Vigil — a defensive-cyber terminal agent for Computer Network Defense. Asset discovery, vulnerability assessment, hardening, detection engineering, threat hunting, incident response — on the infrastructure you defend.

AI-powered terminal coding assistant with 10+ models, persistent agent memory, MCP servers, and semantic code search. Free tier with tool support.

DeepSeek adapter for [`@lythos/agent-adapter`](https://github.com/lythos-labs/lythoskill/tree/main/packages/lythoskill-agent-adapter/). Launches `deepseek serve --http` daemon and communicates via thread API.

Model Context Protocol server for DeepSeek V4 API endpoints with stdio and Streamable HTTP transports.

DeepSeek adapter for Zhivex AI SDK.

n8n community node for DeepSeek V4 models (deepseek-v4-flash, deepseek-v4-pro) with thinking mode control

an easy way to make call to LLMs with function call and tools. tested by: Deepseek, openAI, ollama

A user-friendly DeepSeek AI node, similar to OpenAI, designed to enhance your workflow. npm link: https://www.npmjs.com/package/n8n-nodes-deepseek

Improve Pi prompt/KV cache hit rates with stable prompts, OpenAI-compatible cache keys, proxy compat warnings, and footer cache stats.

Claude Code 多模型代理 — 一���切换 DeepSeek、Qwen、GLM、商汤商量、NVIDIA 等国产大模型，协议自动转换，零配置即用。安全增强版：API Key 加密存储、Bearer 认证、SHA256 验证、速率限制、TLS 支持。LLM API proxy for Claude Code with security hardening.

deepseek adapter for chatluna

LLM Router local routing proxy for OpenAI-compatible Chat Completions APIs.

An agentic coding CLI for DeepSeek models, in the spirit of Claude Code

Smart LLM router — save 85% on inference costs. 55+ models (8 free), one wallet, x402 micropayments.

Unofficial DeepSeek API SDK for JavaScript / TypeScript

DeepSeek 用量实时监控插件 — Claude Code 底部状态栏显示 token、费用、余额

MCP server that lets Claude Code delegate heavy-token tasks to DeepSeek. Claude orchestrates; DeepSeek does the heavy lifting. Zero dependencies.

DeepSeek API toolkit with built-in Brave Search — batteries-included wrapper for chat, tools, and web search

DeepSeek命令行聊天工具

A headless, multi-provider AI agent harness. One install gives you the `cortex` CLI and HTTP server: npm i -g nexus-cortex.

Multi-provider terminal AI assistant — TUI, web UI, and one-shot mode backed by any OpenAI-compatible API

Anthropic SDK to multi-provider streaming bridge - converts Anthropic message format and tool calls to Gemini, OpenAI-compatible APIs

DeepSeek Code CLI — interactive AI coding assistant in the terminal

Terminal AI coding agent for local software development

Jarela — local chat interface for LangGraph agents (multi-provider, single-process, SQLite-backed).

Claudin — Claude Code opened to any LLM (OpenAI, Gemini, DeepSeek, Ollama, and 200+ models)

DeepSeek Web bridge for Codex CLI - Termux/ARM64 ready

Local agent swarm: a conductor model splits missions into parallel sub-agents with real tools, optional sandboxes, and a localhost web UI. Research, forecasting, and software-build (code) modes. Works with DeepSeek, OpenAI, Anthropic, Grok, MiniMax, OpenR

The open-source Claude Code GUI — an IDE-like workbench for parallel AI coding. Drive Claude (default), Codex, DeepSeek, Kimi, or local Ollama in tabs. Terminal, browser & DB bubbles, code review. Self-host on a shared dev box — a seat for every teammate.

Professional AI-powered CLI for developers using DeepSeek API

n8n community node for SiliconFlow AI models - chat completions, vision language models, embeddings, and reranking

Command-line tool for DeepSeek API

Claude Code × 国产大模型一键接入：DeepSeek、Kimi、火山方舟、Qwen、MiniMax、GLM、MiMo、自定义接口

DeepSeek-native coding agent for the terminal — 1M-token context, thinking-mode, full tool-use.

Multi-provider LLM inference library for AI-powered trading strategies. Supports 10+ providers including OpenAI, Claude, DeepSeek, Grok, Mistral with unified API and automatic token rotation.

Web search for Pi using DeepSeek's server side search. Only works with DeepSeek models.

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。

🪼 AI-powered CLI assistant for terminal productivity

Use DeepSeek from the CLI through your logged-in local Chrome or Chromium via CDP.

Atus Code — coding agent CLI for any LLM (fork of OpenClaude)

An AI-powered coding assistant that lives in your terminal

DeepSeek V4 proxy for Claude Code. Anthropic-format streaming, tool-calling, prompt-caching, and live token/cost statusline.

Provider adapters for AgentsKit.

API-first MCP server for multi-model cross-review with unanimous convergence gates.

Transparent wrapper to track LLM API costs in real-time by session, user and model

216 个即插即用的 AI 专家角色定义 — 从前端开发到区块链安全，从小红书运营到抖音策略

Tako CLI — unified launcher for AI coding tools (Claude Code, Codex, Gemini) with multi-agent session management

Cynos — an autonomous AI engineering runtime with evidence-based completion verification.

A small, extensible CLI coding agent with interchangeable Anthropic, Gemini, OpenAI, DeepSeek, Qwen, and local (Ollama) models.

Estimate and compare LLM costs for AI coding projects. Supports 85+ models via OpenRouter. Works with natural language.

Promptbook: Run AI apps in plain human language across multiple models and platforms

V2 manifest-based LLM executor for agnt prompts with CLI

Tau - multi-provider AI coding CLI with Firecrawl-hosted WebSearch. Firecrawl offers 1k searches/month on free trials; just enter your API key.

Torus — a minimal, ICM-structured Agent SDK: agent loop, tools, in-process MCP, markdown-contract subagents, multimodal input, and a free-first model cascade (NVIDIA Kimi K2.6 / DeepSeek V4 → Gemini → Claude) with cost routing.

Run any model with an Anthropic- or OpenAI-compatible API — even your Codex subscription — as Claude Code workflows, agent-team teammates, or one-shot subagents. Your main session's own auth (OAuth or API key) is untouched.

Route multiple AI CLIs (Claude Code, Codex, OpenCode) with isolated env profiles — native Go binary, SHA256-verified download

AI coding agent CLI — 22 LLM providers, 101 models, wiki knowledge engine, OpenCode-inspired TUI, MIT-licensed

本地 AI 助手 — 终端 + 网页双模式，69+ 内置工具（含桌面控制、浏览器自动化、向量记忆搜索），80+ 模型商，4 个消息渠道，ClawHub 兼容，Docker 支持

OpenCode plugin for iFlow.cn - Access Qwen, DeepSeek, Kimi, GLM-5 models with OAuth 2.0, API Key, and CLI Proxy support

Embeddable TypeScript agent SDK for DeepSeek — built-in tools, skills, memory, and MCP.

Universal LLM stream parser that normalizes SSE chunks from OpenAI, Anthropic, Google, and other providers into a single token event API.

Terminal-first coding agent — runs locally with Ollama, DeepSeek, OpenAI, or any OpenAI-compatible endpoint

DeepSeek-native coding agent: cache-first loop, flash-first cost control, tool-call repair.

Multi-agent YAML workflow engine — 216 AI roles, auto DAG parallelism, zero code. One sentence → multiple AI roles collaborate → complete plan in minutes. 10 LLM providers, 7 need no API key.

Vue 3 Composable library for building AI-powered applications, with optional React chat, completion, object, image, video, prompt suggestion, and agent entries. useChat, useCompletion, useEmbedding, useImage, useVideo, useSpeech, useTranscription, useRera

ZER0CODE — Autonomous AI Coding Agent for Expert Penetration Testers

Use NVIDIA NIM models (DeepSeek, Llama, Qwen, Mistral, 100+) with Claude Code. Translates Anthropic API to OpenAI-compatible format.

Talk to 500+ AI models from inside Claude Code. One file. Zero config.

PERUVIANCODE — terminal IA colaborativa con NVIDIA. Comando: peruvian

Convert upstream LLM APIs (Chat Completions / Anthropic Messages) to OpenAI Responses API format. Zero dependencies, works in browser/Node/edge.

OpenAI-compatible API server for DeepSeek

🧬 Reliable interface with automatic fallback for AI LLMs.

100+ LLM models. Pricing, capabilities, context windows. Always current.

Verboo Code — coding agent for the Verboo platform

Splash — Autonomous Agent Platform: CLI + multi-provider agent loop + TUI dashboard + platform bots

TheClawBay provider extension for Pi Coding Agent - access GPT-5, Codex, Claude, Gemini, DeepSeek, open-weight, and image models

AgInTiFlow is a project-aware agent workspace for hybrid wet-dry R&D, hardware-aware intelligence, software automation, and industrial workflows.

AtusCode opens coding-agent workflows to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models

Real-time coding agents that work like a live team on one shared repository.

Run 400B+ open coding models on your codebase without the hardware bill. Ollama Cloud first — OpenAI, Anthropic, and Gemini when you need them.

Mock API server for Codex with sk- key validation

DeepSeek V4 原生 AI 编程 Agent CLI — 面向中文开发者

Zero CLI to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models

Minimalist AI CLI assistant — one shell tool, filesystem memory, auto context migration

Terminal coding agent optimized for DeepSeek V4 prefix cache

Multi-agent AI collaboration platform for end-to-end software delivery

Context-aware MCP prompt compiler with a composable pipeline: clarify_with_user → ground_prompt OR optimize_prompt → critique_prompt, all in one call via compose_prompt. Persistent memory, knowledge packs, explicit token-budget curation, reflective learni

AI Novel Agent v2.1 — 46 built-in Skills × config-driven quality engine (check_chapter 100pt scoring + fix_chapter auto-repair) × multi-agent sandbox × 3-level writing cache. Terminal-based Chinese web novel creation assistant.

n8n community node for SiliconFlow (硅基流动). Zero runtime dependencies. Provides a SiliconFlow action node (Chat / Vision / Embeddings / Image / Rerank / Audio TTS+ASR / Video) and a LangChain-compatible Chat Model node for AI Agents. Installs cleanly witho

Claude Code opened to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models

Universal AI adapter - One API for 15 providers (Ollama, Cerebras, OpenRouter, Qwen, Kimi, Mistral, Perplexity, Minimax, Z AI, OpenAI, Anthropic, Groq, DeepSeek, Gemini) with Compare All, fallback, streaming

n8n community node for DeepSeek chat models (Pro / Flash) with reasoning_content (Chain-of-Thought) support, usable as a LangChain sub-node inside the AI Agent and Basic LLM Chain.

A lightweight TypeScript SDK for interacting with a multi-model OpenAI-compatible API, including Claude 3.5, LLaMA, and DeepSeek.

LLM client factory: DeepSeek + Anthropic providers with token pricing

Whisper to free web LLM chat UIs (Qwen, ChatGPT, Claude, DeepSeek, GLM) and expose them over one local HTTP API — no API keys needed.

Core primitives for DeepWhale: i18n, session JSONL, compaction, types

OpenCode plugin for iFlow providing access to Qwen, DeepSeek, Kimi, GLM, and iFlow ROME models with auto-config and headless OAuth support

Stop AI coding sessions from bloating - compress, deduplicate, and stabilize LLM context

Generates AI-powered natural-language summaries of git diffs for code review.

Conversational state engine for TypeScript where the AI understands, but the code is in control

统一 LLM Provider npm 包：一套统一结构接入 Gemini / Claude / OpenAI Compatible / OpenAI Responses / DeepSeek

See exactly what your coding agent sends to the model — a local logging reverse-proxy + web dashboard for Claude Code, Codex, DeepSeek-TUI, Reasonix, and Kimi. Just run `ccglass`.

Give your AI coding agent a cheap DeepSeek coworker. Delegate bulk reads, boilerplate, and doc updates to save 60-70% of your token budget.

DeepSeek prefix cache optimization for pi — date/CWD freeze, hit-rate telemetry, cache-friendly compaction, and TUI overlays

OpenCode plugin that routes images from text-only models to an @img vision subagent.

OpenCode plugin for LLM prompt caching, token savings, and KV cache reuse across AI agent sessions

Makora provider extension for pi - Access DeepSeek V4, GLM 5.2, Kimi K2.7 Code, Llama 3.3, Qwen 3.6, and more through the Makora inference API

excoder — AI coding assistant for any LLM — ScrapeGoat, DeepSeek, OpenAI, Gemini, Ollama, Groq, and 200+ models

DeepSeek V4 terminal coding agent & constitutional harness — Rust TUI with MCP, sub-agents, and session persistence

DeeperCode - 一句话生成完整项目的 AI Agentic CLI 工具

Claude Code API 切换器（命令 xx）：在官方账号与第三方 Anthropic 兼容 API 间切换，纯环境变量、不碰 Claude Code 配置文件。

AI-powered coding assistant CLI using DeepSeek API

MinerU output linter/fixer — LLM tool-use loop that restructures (never generates) MinerU content_list. Machine-verified fidelity: C_out ⊆ C_in. Rust core via napi-rs.

Fix reasoning_content 400 errors for DeepSeek/Kimi/GLM/MiMo/MiniMax in OpenCode

Multi-agent AI code review for git -- parallel agents with confidence scoring

An AI agent with a real self — runs locally, has desires, keeps a journal, evolves over time.

DeepWhale CLI: DeepSeek-first AI coding agent. Linear sessions, 6 tools, Docker sandbox.

Terminal coding agent with model-backed runtime, TUI, and workflow gates.

Extract valid JSON from an LLM response, even when it is wrapped in reasoning/thinking tags, markdown fences or prose. Zero dependencies.

Validate-then-repair extension for pi — fixes common LLM tool-call mistakes (null fields, stringified arrays, wrong field names, anchor bleed) before tools execute

Manifest-based LLM executor for Studio agents with CLI

Core AI functionality for Vue.js components

rhachet brain.atom adapter for fireworks ai open-source models

Claude Code 多模型代理 — 一键切换 DeepSeek、Qwen、GLM、Moonshot 等国产大模型，协议自动转换，零配置即用。LLM API proxy for Claude Code with DeepSeek, Qwen, Anthropic, OpenAI support.

Dev Shell Companion — a CLI coding agent that lives in your terminal

Vue2/Vue3 UIKit for AI Desk

LLM-driven web search and content extraction extension for Pi — Tavily, Exa, Anysearch, Gemini, DeepSeek, Jina, and Firecrawl.

Parse streaming SSE responses from OpenAI, Anthropic, Gemini and OpenAI-compatible providers into one unified event format. Text, reasoning and tool-call deltas. Zero dependencies.

Per-process Claude Code env launcher with default args management (global + per-env), interactive picker, shell completion, and env-leak protection. One command to inject provider env (DeepSeek/Kimi/GLM/CCR/...) and start claude.

Improve OMP prompt/KV cache hit rates with stable prompts, OpenAI-compatible cache keys, proxy compat warnings, and footer cache stats.

MinerU output linter/fixer — LLM tool-use loop that restructures (never generates) MinerU content_list. Machine-verified fidelity: C_out ⊆ C_in. Rust core via napi-rs.

Pi extension: detects and interrupts infinite thinking-block and tool-call loops in real time before they exhaust your context window.

Normalize OpenAI, Anthropic and Gemini API errors into one shape: category, retryable flag and Retry-After delay. Zero dependencies.

DeepSeek API quota monitor with MCP integration — live balance, cost tracking, and session stats in Claude Code

最小化 Agent 系统 —— 10 工具 + 插件系统 + workflow DSL + 自动压缩 + OpenAI 兼容 + Ink TUI；NodeNext + tsc 原地编译，dev 用 Bun .ts、install 用 Node .js（学习/教学用）

A provider-agnostic LLM core for Node.js, inspired by ruby-llm.

The first MCP server that verifies AI outputs in real-time — 6-dimension contract validation (structure, schema, latency, cost, identity, integrity) with automatic self-healing failover across 9+ LLM providers. BYOK, zero-dependency, one-line JSON config

AI-powered code review CLI for git changes

AI-powered CHANGELOG generator from Git history. DeepSeek + OpenAI + Anthropic.

Empathy opens coding-agent workflows to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models

A Codex-led read-only worker pool that delegates workspace exploration and high-context analysis to OpenAI-compatible models.

A robust utility to repair JSON strings - fix malformed or broken JSON, especially from LLM output like ChatGPT.

Local proxy server that converts any Chat Completions / Anthropic Messages API into OpenAI Responses API so Codex and Claude Code can use any LLM.

MCP vision proxy v0.2 — fork-merge of mature vision MCPs. Multi-model fallback, compare_images, cache, CLAUDE.md rules for DeepSeek text in VS Code / Claude Code.

Pi extension for monitoring Z.ai, DeepSeek, and OpenAI Codex usage

Tensorix provider extension for pi - Access DeepSeek, GLM, Kimi, Qwen, MiniMax, Llama, and more through the Tensorix API

Smart LLM router — save 85% on inference costs. 55+ models (11 free), one wallet, x402 micropayments.

Chinese-first DeepSeek-powered terminal coding agent for personal developer workflows.

AI coding agent powered by DeepSeek via browser automation — no API key needed. Performance-optimized (30-40% faster). New --headless parameter for interactive mode. Enhanced with comprehensive security.

Headless, configurable in-browser LLM agent on the Vercel AI SDK: multi-provider bring-your-own-key (OpenAI, Anthropic, Google, xAI, DeepSeek, gateway, openai-compatible) AND local WebGPU/WebLLM, native + prompted tool-calling, structured output, an encry

Global CLI: freeclaude — Claude Code opened to any LLM (OpenAI, Gemini, DeepSeek, Ollama, etc.)

MinerU output linter/fixer — LLM tool-use loop that restructures (never generates) MinerU content_list. Machine-verified fidelity: C_out ⊆ C_in. Rust core via napi-rs.

UPP: Unified Provider Protocol for AI inference

Token-aware analyst/worker workflow and token ledger extension for Pi Dev coding agents.

AI Gateway with visual fallback routing, hybrid multi-backend search, and protocol translation for Claude Code & Codex

Soul-driven AI agent with Second Brain memory, permission-hardened tools, token budgets, and multi-channel access. Runs 24/7 from CLI or Telegram.

MinerU output linter/fixer — LLM tool-use loop that restructures (never generates) MinerU content_list. Machine-verified fidelity: C_out ⊆ C_in. Rust core via napi-rs.

Tenseuron Protocol CLI — mine and validate AI tasks from any machine. Cloud APIs (DeepSeek/OpenAI/Gemini/etc.) or local LLMs (Ollama/LM Studio).

The complete Alibaba provider for pi — Plan subscription + Cloud pay-per-token, International + China endpoints, Anthropic + OpenAI shapes, native thinking levels. Qwen 3.7 Max, Qwen 3.7 Plus, Qwen 3.6 Max, Qwen 3.6 Plus, DeepSeek V4 Pro, Kimi K2.6, GLM-5

一键配置 OpenClaw 使用 InsCode AI - 只需提供 API Key

CORTEX — Autonomous AGI Terminal. Any LLM, one command. NVIDIA, OpenAI, Gemini, Groq, Ollama and more.

Local OpenAI Codex Responses API gateway for DeepSeek Chat Completions.

Multi-agent harness for building applications autonomously with any LLM. Researcher, Planner, Curator, Generator, Evaluator, Documenter pipeline. Supports Claude, GPT, Gemini, DeepSeek, Ollama, and Claude Code subscriptions. MCP server for Cursor/Windsurf

Synapse - AI Gateway & Intelligence Platform with Neural Router, Semantic Cache, Persistent Memory, Self-Learning, and 5+ AI Providers

Vigil — an offensive-cyber terminal agent for Computer Network Attack. Exploitation, payload delivery, persistence, lateral movement, credential harvesting, command and control — on authorized target infrastructure.

A lightweight, elegant, and feature-complete TypeScript AI Agent framework

Convert chat conversations and responses between OpenAI, Anthropic and Gemini. Tool calls, images, audio, documents and roles handled. Zero dependencies.

A translator in your command line

Priority-based LLM routing across multiple providers to reduce cost with free-first and fallback chains.

OpenClaude opens coding-agent workflows to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models

AI-powered coding toolbar for any web application. Select elements, capture context, and let AI modify your codebase in real-time.

Fast TypeScript AI agent framework — per-request agents, 30+ model providers, 100+ integrations, 20+ vector DBs, 10+ databases, sessions, memory, knowledge, tracing, evals, HITL, teams, and workflows.

Whisper to free web LLM chat UIs (Qwen, ChatGPT, Claude, DeepSeek, GLM) and expose them over one local HTTP API — no API keys needed.

Convert any JSON Schema into a valid tool / function calling schema for OpenAI, Anthropic, Gemini and MCP. Zero dependencies.

终端 AI 助手 + 工具调用闭环,对接任意兼容 OpenAI SDK 的 LLM endpoint。流式输出、Markdown 渲染、会话持久化。

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

A DeepSeek-powered coding agent CLI.

Autonomous AI coding agent — explores your codebase, diagnoses root causes, writes fixes, and runs tests. Supports Claude, Gemini, DeepSeek, and Kimi K2.

XCode - AI-powered coding assistant with OpenRouter, GPT/OpenAI-compatible, and Gemini support.

AuroraCoder — an autonomous AI coding agent. Install via npm and run directly on your machine (no Docker required).

Critiq — Zero-noise AI Code Review Agent for developers. CLI-first. Pipe `git diff` and get AI-powered reviews in Chinese.

终端原生 AI 编程助手 — DeepSeek 驱动，50+ 工具，对话记忆，虚拟浏览器，Ink 全屏界面

Configure Claude Code to use DeepSeek API as backend

Universal WorkorAI talent marketplace Agent Skill and MCP installer for Codex, Claude Code, OpenCode, Cursor, Qwen Code, Antigravity, Deep Code, and skill registries.

An SDK written in Typescript for the [Inference Gateway](https://github.com/inference-gateway/inference-gateway).

uni-app Vue2/Vue3 UIKit for AI Desk

Core types, factory, and session management for Halo AI SDK — cache-aware agent with automatic tool-call loop

TypeScript backend for the Godot Daedalus editor assistant plugin.

MinerU output linter/fixer — LLM tool-use loop that restructures (never generates) MinerU content_list. Machine-verified fidelity: C_out ⊆ C_in. Rust core via napi-rs.

A simple, unified NPM-based interface for interacting with multiple Large Language Model (LLM) APIs, including OpenAI, AI21 Studio, Anthropic, Cloudflare AI, Cohere, Fireworks AI, Google Gemini, Goose AI, Groq, Hugging Face, Mistral AI, Perplexity, Reka A

DeepSeek AI-powered CLI agent for code assistance and automation