Awesome Ai Agents 2026
Section: Data Analysis · Chat with your data. NL to Pandas/SQL.
Entry
Appears in 5 awesome lists
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
Section: Data Analysis · Chat with your data. NL to Pandas/SQL.
Section: Data Analysis & Visualization · Conversational data analysis using natural language
Section: Chatbots · 4, Anthropic, VertexAI) and RAG.
Section: Useful Python Tools for Data Analysis · Conversational data analysis using LLMs and RAG.
Section: Data Science and Analytics · Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
robot: The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. Features: Generate Text, Audio, Video,…
Microsoft's multi-agent conversation framework with a complete AgentChat layer covering agent loop, tool integration, termination conditions, and human-in-the-loop. The most comprehensive open-source reference for large-scale multi-agent harness design.
TypeScript-native agent framework (from the Gatsby team) with 22K+ stars and 300K+ weekly npm downloads. Connects to 40+ providers through one standard interface, with built-in workflows, RAG pipelines, and agent orchestration. The @mastra/deployer handles serverless deployment, and the eval…
FastChat is a platform for training, serving, and evaluating large language model chatbots, featuring an open-source distributed multi-model system, API compatibility, and a dataset for LLM conversations github | demo | discord | twitter
Self-hosted AI assistant that connects Claude to Telegram (and 7 other channels) from a single deployment. Supports hooks, plugins, and tools. Telegram setup: https://clawdbot.blog/channels/telegram/
is an ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue based on LLaMa.
Universal memory layer for AI agents. Simple API to create RAG applications over any dataset with support for multiple vector stores, embedding models, and LLM providers. Apache 2.0 licensed.
Open-source ChatGPT equivalent experience for both open and close source LLMs, embedders, and vector databases. Supports unlimited documents, threads, and concurrent users and management all in a very clean UI.