Open Source AI Agents
Discover 406 open source AI Agents repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. AI Agents projects here are most often combined with Python, Developer Tools and MCP. Last updated October 4, 2026.
406 repositories · updated October 4, 2026
Memary: Add Memory and Knowledge Graphs to AI Agents
Memary is a memory layer for autonomous agents that combines a knowledge graph with user-focused memory to inform responses over time. It suits developers building personalized agents who can manage local models, database connections, and API credentials.
Memori: Give AI Agents Persistent Memory
Memori adds structured, persistent memory to LLM applications by capturing agent execution and conversations. Its Python and TypeScript SDKs integrate with existing models and data infrastructure, with managed cloud and BYODB options.
sandbox-sdk: Run Code in Cloudflare Edge Sandboxes
Cloudflare Sandbox SDK helps Workers run untrusted or generated code in Linux containers managed through Durable Objects. It adds file transfer, S3-compatible mounts, and directory backups for isolated per-user or per-task environments.
Agentless: Find and Repair Bugs with LLMs
Agentless uses language models to localize bugs, generate candidate code patches, and validate them without an agent-based workflow. It is aimed at developers and researchers evaluating automated software repair, especially on SWE-bench.
ElatoAI: Build Realtime Voice AI Devices with ESP32
ElatoAI connects ESP32 devices to realtime voice AI through secure WebSockets and edge functions. It is for developers building talking toys, companions, or other connected devices that need speech-to-speech models and a web-based control app.
local-deep-research: Research with Local or Cloud AI
Local Deep Research turns complex questions into cited reports by coordinating LLMs with web, academic, and private-document search. It suits researchers and privacy-conscious teams who want a self-hostable tool and control over models and data.
wassette: Run WebAssembly Tools Through MCP
Wassette lets AI agents load and use WebAssembly Components through the Model Context Protocol. It is aimed at developers who want reusable tools running in Wasmtime’s security sandbox, but the project warns that it is not production-ready.
deepscrape: Scrape Websites and Extract Structured Data
DeepScrape is a self-hosted TypeScript service for scraping and crawling websites, returning clean content or structured data. It combines HTTP fetching, Playwright, optional LLM extraction, and APIs for building data pipelines and agent workflows.
airweave: Retrieve Shared Context for AI Agents
Airweave syncs data from connected apps, databases, and documents into a unified search layer for AI agents and RAG systems. It suits teams that want reusable retrieval infrastructure instead of building separate ingestion pipelines for each agent.
Agent-S: Automate Desktop Tasks Through a GUI Agent
Agent-S is a Python framework that uses screenshots, mouse clicks, and keyboard input to carry out natural-language tasks in desktop applications. It suits research and automation workflows that need an agent to interact with a real computer interface.
awesome-ai-agents: Browse Curated Agentic AI Resources
A curated directory of agentic AI projects, tools, and frameworks organized by category. Use it to explore the ecosystem, compare project listings, and find resources for a specific agent-building need.
opik: Trace, Evaluate, and Monitor LLM Applications
Opik is a platform for tracing and evaluating LLM applications, RAG systems, and AI agents. Teams can use it to inspect workflows, run evaluations, and monitor deployments, either self-hosted or through Comet Cloud.