Keploy is an open‑source AI test automation agent that uses eBPF to record live traffic and generate deterministic unit, integration, and API tests with mocks/stubs. It integrates with CI/CD, supports multiple languages, and uses multi‑model LLMs for test generation and self‑healing.

Keploy

keploy

An open‑source AI agent that auto‑generates and maintains unit, integration, and API tests with mocks.

Jina AI is an open‑source platform (founded 2020) offering modular AI tools for building neural search, RAG and agentic applications. Its Search Foundation includes embeddings, rerankers, Reader, DeepSearch, classifiers, segmenters, and AgentChain orchestration to support complex multimodal retrieval and reasoning.

Jina AI

jina-ai

A multimodal search foundation platform powering embeddings, rerank, classification & RAG workflows.

11.ai by ElevenLabs is an alpha‑stage, voice‑first AI assistant built on Model Context Protocol (MCP). It connects securely to tools like Slack, Linear, Perplexity, Notion to research information, update systems, and take sequential actions—all via natural voice or text interaction.

11.ai

11-ai

A voice‑first MCP‑powered AI assistant that integrates with your tools to research, communicate, and act via voice.

Gemini CLI is Google's open‑source AI agent that integrates Gemini 2.5 Pro into the terminal. It supports a 1 million‑token context window, reasoning-and-act loops, Model Context Protocol, web grounding with Google Search, multimodal tasks (code, content, images, video), file manipulation, shell execution, and integration with Gemini Code Assist and MCP tools. It works on Windows, macOS, and Linux.

Gemini CLI

gemini-cli

An open‑source command‑line AI agent bringing Gemini 2.5 Pro into your terminal for coding, research, content and task automation.

Kimi‑Dev (72B) is an open‑source coding language model by Moonshot AI, fine‑tuned via reinforcement learning to autonomously fix bugs and write tests, achieving state‑of‑the‑art SWE‑bench performance.

Kimi‑Dev

kimi-dev

Open‑source coding LLM optimized for automated debugging and issue resolution tasks.

MiniMax‑M1 is an open‑weight, hybrid Mixture‑of‑Experts large language model offering natively a 1 million token context window. It uses lightning attention and efficient RL training (CISPO) to excel at long-context reasoning, tool-use, coding, and mathematics. Released under Apache 2.0, it supports structured function calling and is deployable via vLLM, Transformers, or API.

MiniMax‑M1

minimax-m1

Open‑source large‑scale reasoning model with 1 million token context and hybrid Mixture‑of‑Experts architecture.

Chroma is an open-source, AI-native vector database built for storing and querying embeddings alongside metadata. It supports full‑text and multimodal search, scalable retrieval, and powers retrieval‑augmented generation workflows. Available as both a local SDK and a private‑preview managed cloud, Chroma offers strong developer ergonomics and extensible integrations for building production‑grade LLM applications.

Chroma

chroma

An open‑source vector database and embeddings engine for building retrieval‑augmented AI applications.

AMIE (Articulate Medical Intelligence Explorer) is a research AI system developed by Google Research and DeepMind, designed to engage in diagnostic medical conversations. Built upon the Gemini 2.0 Flash model, AMIE integrates a state-aware reasoning framework that allows it to adapt its responses based on the evolving context of a clinical dialogue. This enables AMIE to intelligently request, interpret, and reason about visual medical information, such as skin photos, ECGs, and lab results, enhancing its diagnostic capabilities. In evaluations using Objective Structured Clinical Examinations (OSCEs), AMIE demonstrated performance comparable to or exceeding that of primary care physicians in areas like diagnostic accuracy, multimodal data interpretation, and communication skills. While AMIE shows promise in augmenting clinical decision-making, further research and validation are required before real-world deployment.

AMIE

amie

A multimodal AI diagnostic agent that conducts clinical conversations and interprets medical images for accurate diagnoses.

AlphaEvolve is an evolutionary AI coding agent developed by Google DeepMind, designed to autonomously discover and optimize complex algorithms across various domains. Leveraging the capabilities of Gemini 2.5 Flash and Pro models, AlphaEvolve employs an ensemble approach that balances computational throughput with solution quality. It utilizes an evolutionary framework where large language models generate candidate algorithms, which are then evaluated and refined through automated processes. This system has achieved notable successes, including surpassing the 56-year-old Strassen algorithm for matrix multiplication and optimizing data center scheduling, leading to significant efficiency gains. AlphaEvolve's ability to generate provably novel and correct algorithms marks a significant advancement in AI-driven scientific discovery.

AlphaEvolve

alphaevolve

A Gemini-powered AI coding agent that autonomously discovers and optimizes complex algorithms.

Google's AI Co-Scientist is a multi-agent system built on Gemini 2.0, designed to function as a virtual scientific collaborator. It assists researchers by generating novel hypotheses, designing experiments, and analyzing complex datasets. The system employs specialized agents that mimic the scientific method through processes like generation, reflection, and ranking. In collaboration with institutions like Stanford University and Imperial College London, the AI Co-Scientist has demonstrated its ability to identify novel biological mechanisms and potential therapeutic targets, showcasing its potential to accelerate scientific and biomedical discoveries.

Google AI Co-Scientist

google-ai-co-scientist

A multi-agent AI system that collaborates with scientists to generate hypotheses and accelerate biomedical research.

Agent Network Protocol (ANP) is an open-source communication protocol designed to facilitate secure, decentralized interactions among AI agents. It aims to become the 'HTTP of the Agentic Web Era' by providing a standardized framework that enables agents to connect, communicate, and collaborate efficiently. ANP's architecture comprises three layers: the Identity Layer for decentralized authentication using W3C DID standards, the Meta-Protocol Layer for dynamic protocol negotiation, and the Application Layer for semantic-based capability descriptions. This structure ensures interoperability, scalability, and secure communication across diverse AI systems.

Agent Network Protocol

agent-network-protocol

An open-source protocol enabling secure, decentralized communication among AI agents.

Hugging Face's Open Computer Agent is an open-source AI tool designed to perform web-based tasks by emulating human interactions within a virtual Linux desktop environment. Powered by vision-language models like Qwen2-VL-72B and frameworks such as smolagents and E2B Desktop, it can navigate websites, fill out forms, and retrieve information based on natural language prompts. Operating through a browser interface, the agent simulates mouse and keyboard actions to execute tasks. While still in its experimental phase, it showcases the potential of AI agents in automating routine digital activities.

Hugging Face Open Computer Agent

hugging-face-open-computer-agent

An open-source AI agent that automates web tasks by simulating user interactions in a virtual Linux environment.

Explore AI Agents with free pricing