AI codebase search

Serena

Agents · Bring your own (Claude, GPT, etc.)

7.1

Open-source MCP toolkit that gives coding agents IDE-grade symbol search, refactoring, and editing across 40+ languages.

CocoIndex

RAG · Bring-your-own (embeddings + LLM)

6.9

Open-source incremental data framework that keeps RAG indexes and agent context continuously fresh.

Claude

Featured

Writing · Claude Opus / Sonnet

9.6

Anthropic's flagship assistant for long-form writing, analysis, and coding.

Semantic Kernel

Agents · Multi-model

8.4

Microsoft's open-source SDK for wiring LLMs, plugins, and agents into enterprise .NET, Python, and Java apps.

AudioCraft

Audio · MusicGen, AudioGen, EnCodec

8.2

Meta's open-source research toolkit for generating music and sound effects from text via a single autoregressive language model.

Hermes Agent

Agents · Multi-model (300+ via Nous Portal)

8.2

Open-source multi-channel AI agent with persistent memory, scheduling, and subagent delegation from Nous Research.

Windsurf

Coding · SWE-1.6 Fast (plus Claude Agent, OpenCode via ACP)

8.1

AI-native IDE turned agent command center, now folded into Cognition's Devin lineup.

Cody

Coding · Claude / GPT / Mixtral (configurable)

8.0

Sourcegraph's AI coding assistant — codebase-aware via their search index.

Sesame

Audio · Sesame CSM (1B / 3B / 8B)

8.0

Conversational voice AI aiming to cross the uncanny valley with context-aware, emotionally aware speech.

AnythingLLM

RAG · Multi-model

7.9

Open-source desktop and self-hosted app that turns your documents into a private chat-and-agent workspace.

Manus

Agents · Multi-model

7.9

Generalist agent for research, code, and web tasks.

RAPIDS

Coding

7.7

NVIDIA's open-source suite of GPU-accelerated drop-in replacements for pandas, scikit-learn, and NetworkX.

AgentMemory

Agents · Multi-model (Claude, Gemini, MiniMax, OpenRouter)

7.3

Open-source persistent memory runtime for AI coding agents, with hybrid retrieval and zero external dependencies.

MMagic

Image Generation · Multi-model (Stable Diffusion, ControlNet, StyleGAN, GANs, diffusion)

7.3

OpenMMLab's research-grade toolbox for image and video generation, restoration, and editing.

MCP Toolbox for Databases

Agents · Multi-model

7.2

Open-source MCP server that wires AI agents and IDEs straight into 50+ production databases with auth, pooling, and observability baked in.

Weco AI

Evaluation · Multi-model (LLM + AIDE tree search)

7.2

Autoresearch engine that iteratively rewrites code to optimize against a numeric evaluation metric.

BGE (BAAI General Embedding)

RAG · BGE / bge-m3 / bge-reranker

7.1

Open-source embedding and reranker models from BAAI that anchor a huge share of production RAG stacks.

Tiledesk

Agents · Multi-model

7.1

Open-source conversational AI platform for building multi-channel support agents and automation workflows.

AgentGPT

Agents · GPT-3.5 (BYO key for others)

6.9

Browser-based autonomous AI agent builder that chains GPT calls toward a goal you define.

ChatGPT for Google

Agents · Multi-model (GPT-4, Claude 2, others)

6.9

Browser extension that pipes GPT-4, Claude and other LLM answers into your existing search results page.

Folo

Agents · DeepSeek

6.9

Open-source AI RSS reader that summarizes feeds and cuts noise from 1M+ sources.

GoCodeo

Coding · Multi-model (Claude 3.5/3.7, Gemini 2.5 Pro, GPT-4o, o3-mini, DeepSeek-R1)

6.9

VS Code agent that builds, tests, and debugs full-stack apps across 25+ frameworks with multiple frontier LLMs.

Haystack

RAG · Multi-model

6.9

Open-source Python framework from deepset for building production RAG pipelines and LLM agents.

Mintlify

Coding · Multi-model

6.8

AI-native documentation platform that writes, maintains, and serves docs to humans and LLMs.

AutoGen

Agents · Model-agnostic: OpenAI (GPT-4o, GPT-4.1, o-series), Azure OpenAI, Anthropic Claude, Google Gemini, Ollama, and any OpenAI-compatible local model (vLLM, llama.cpp)

Microsoft's open-source framework for multi-agent AI applications

Chroma MCP

MCP Servers

Official MCP server that gives LLM clients direct access to the Chroma vector database.

claude-mem

Agents · Model-agnostic — works with the models used by the connected agent (Claude, GPT, Gemini, etc.) via MCP

Persistent, cross-agent memory for Claude Code and other coding assistants

Exa MCP Server

MCP Servers · Exa neural search index (in-house)

Web search, code search, and company research for AI assistants over MCP

gpt-engineer

Agents · OpenAI GPT (default), Anthropic Claude, Azure OpenAI, and open-weights models like WizardCoder via configuration

Describe software in natural language, watch an AI agent write, run, and improve it.

Kritt

Agents · Codex and Claude Code (as agent harnesses)

AI-assisted code security research with parallel agents and verified findings

Magic.dev

Coding · In-house frontier code models (including a long-term-memory 'LTM' model family with reported 100M-token context)

Frontier code models with ultra-long context aimed at automating software engineering

MemPalace

Agents · Embedding backends: embedding-gemma-300m (multilingual) or all-MiniLM-L6-v2 (English). No LLM required for retrieval.

Open-source, local-first AI memory system for LLM agents

Notion MCP Server

MCP Servers

The official Notion MCP server: give Claude, Cursor, and Copilot typed access to your Notion pages, databases, and comments.

Onyx

RAG · LLM-agnostic — routes to OpenAI (GPT-4o/GPT-5), Anthropic Claude, Google Gemini, Azure OpenAI, AWS Bedrock, or local Ollama/vLLM models

Open-source AI chat connected to your docs, apps, and people

OpenClaude

Coding · Model-agnostic — routes to OpenAI, Gemini, Grok, Codex, Ollama, LM Studio, GitHub Models, DeepSeek and 200+ others

Open-source, model-agnostic terminal coding agent

Playwright MCP

MCP Servers

Microsoft's official Model Context Protocol server for browser automation via Playwright.

Qdrant MCP Server

MCP Servers · FastEmbed (default: sentence-transformers/all-MiniLM-L6-v2); pairs with any MCP-capable LLM such as Claude 3.5/4, GPT-4o, or local models

Official Qdrant MCP server that turns a vector database into a semantic memory layer for Claude, Cursor, Windsurf, and any MCP client.

Redis MCP Server

MCP Servers

Archived reference MCP server exposing basic Redis set/get/delete/list to any MCP-capable LLM client.

Setoku

RAG · Model-agnostic (MCP); commonly paired with Claude / Claude Code

Open-source MCP knowledge server that makes any AI fluent in your company data

Sim

Agents · Multi-model: OpenAI, Anthropic, Google, DeepSeek, xAI, Cerebras, Groq, Sakana AI

Open-source AI agent workspace — build visually, conversationally, or with code

Tabby

Coding · DeepSeek-Coder, Qwen2.5-Coder, StarCoder, CodeLlama, or any OpenAI-compatible endpoint (Mistral, etc.)

Open-source, self-hosted AI coding assistant

Turbopuffer

RAG · bring-your-own embeddings (any provider)

Fast search on object storage

Vectara

RAG · In-house Boomerang (retrieval) and Mockingbird (generation) plus BYOM for GPT, Claude, Gemini, and open-weight LLMs

Enterprise agent platform with built-in retrieval, grounding, and hallucination controls

Voyage AI

RAG · in-house (voyage-3.5, voyage-4 series, voyage-code-3, voyage-finance-2, voyage-law-2, voyage-multimodal-3.5, voyage-context-3, rerank-2.5)

State-of-the-art embedding models and rerankers purpose-built for retrieval and RAG.

Cursor

Featured

Coding · Claude / GPT (configurable)

9.5

AI-first VS Code fork — chat, edit, and agentic coding in one IDE.

Warp

Coding · Multi-model: OpenAI, Anthropic Claude, Amazon Bedrock, plus BYO via OpenRouter and LiteLLM

8.8

The agentic development environment, from the terminal up

Cline

Coding · Model-agnostic: Claude (Anthropic), GPT (OpenAI), Gemini (Google), DeepSeek, Grok, Mistral, Cerebras, plus local Ollama/LM Studio

8.7

Open-source agentic coding assistant that plans, edits, and runs code inside your IDE

Elasticsearch Vector Search

RAG · BYO embeddings (OpenAI, Cohere, Hugging Face, Mistral, Bedrock, Vertex, Azure) plus Elastic's built-in ELSER sparse model and E5 dense model

8.7

Hybrid vector + keyword search in the enterprise-grade Elasticsearch engine