57 agents available in the DeepSeek directory
Pre-built AI agents with specialized instructions for specific tasks โ from coding and writing to research and analysis. Each agent is ready to deploy with a single click.
Control different agents with agents. Free, local, workspace for AI agents. Let one agent (Claude Code, Codex, Hermes, DeepSeek, Kimi, ...) spawn and drive others over MCP. No API keys, no changes to your Agent.md or Claude.md. TUI, Web UI, CLI, MCP in one package.
Cost saving Cognitive Architecture for AI Agents. Infinite Context. Perfect Recall. Zero Hallucinations.
Elixir bridge package that seamlessly integrates Legion's code-execution agents with DeepSeek's powerful reasoning models
ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source coding-agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimit, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs.
๐ค VoiceDev - The Ultimate AI Agent Platform with 250+ Tools, 123+ Skills, 17 Providers, 95+ Verified Models | GPT-5.4, Claude 4.6, Gemini 3.1 | Custom Endpoints | Built by an 11-year-old Egyptian ๐ช๐ฌ
Run a modular agent runtime on ESP32-S3 that manages LLMs, tools, memory, and channels for efficient message processing.
Automate Windows deployment of OpenClaw with a portable Capp that isolates environments, handles dependencies, and optimizes network settings.
Multi-model AI agent ecosystem with 5-layer escalation hierarchy, exponential backoff retries, and automatic fallback chaining across Claude, GLM, and DeepSeek
PARL (Parallel-Agent Reinforcement Learning) is a training paradigm that teaches models to decompose complex tasks into parallel subtasks and coordinate multiple agents simultaneously.
PARL (Parallel-Agent Reinforcement Learning) is a training paradigm that teaches models to decompose complex tasks into parallel subtasks and coordinate multiple agents simultaneously.
Clouisle is an enterprise-grade knowledge base and intelligent AI Agent platform built on a distributed architecture. It transforms disparate data systems into actionable insights, while empowering intelligent agents to drive business decision-making and automation.
LuaN1aoAgent is a cognitive-driven AI hacker. It is a fully autonomous AI penetration testing agent powered by DeepSeek V3.2. Using dual-graph reasoning, LuaN1ao achieves a success rate of over 90% on the XBOW Benchmark, with a median exploit cost of just $0.09.
LuaN1aoAgent is a cognitive-driven, fully autonomous AI penetration testing agent powered by dual-graph reasoning. It is developed by the Intelligent Offensive and Defensive Security Team led by Professor Lu Hui, Dean of the Institute of Cyberspace Security at Guangzhou University.
A minimal RAG/agent orchestration framework
Enable autonomous AI workflows with a local-first, zero-trust Rust framework for high-performance multi-agent orchestration and deterministic execution.
โก๏ธ Open-source AI Gateway โ Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & end-to-end tracing.
โก๏ธ Open-source AI Gateway โ Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & end-to-end tracing.
Super lightweight Ollama + Qwen Code alternative to run Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
Super lightweight Ollama + Qwen Code alternative to run Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
Open source Twitter AI Agent to post-tweet, schedule-tweet, auto-reply, auto-engage using X API and Browser Cookies
Cerno is a local-first research platform that leverages agentic AI to break down complex queries into verifiable, multi-step workflows. Switch seamlessly between cloud LLMs and self-hosted models, track every reasoning step, and optimize cost and tokensโall while keeping your data on your machine.
Cerno is a local-first research platform that leverages agentic AI to break down complex queries into verifiable, multi-step workflows. Switch seamlessly between cloud LLMs and self-hosted models, track every reasoning step, and optimize cost and tokensโall while keeping your data on your machine.
AMG-RAG (Agentic Medical Graph-RAG) is a comprehensive framework that automates the construction and continuous updating of Medical Knowledge Graphs (MKGs), integrates reasoning, and retrieves current external evidence for medical Question Answering (QA).
Agentic Web Search with Google API is an intelligent assistant that uses Agentic AI and the Google Custom Search API to perform live, deep web searches in response to user queries