A Lisp with first-class LLM primitives, implemented in Rust

The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)

Deploy production-ready AI services in minutes. One YAML file for agents, RAG pipelines, and MCP servers — run anywhere. Inspired by docker-compose.

A standardized framework for enhancing how LLMs process and respond to prompts through composable decorators, featuring an official open standard specification and Python reference implementation. Claude Code plugin and MCP server integration.

Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows, an autonomous runtime watchdog, and a pixel-art web dashboard.

LLM agents as your hyperparameter optimizer.

1flowbase: self-hosted AI gateway with protocol translation, dispatch, chat logs, built-in backend & React blocks to combine AI with business data. All managed by your Agent via MCP.

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace, to navigate, interact with, and extract information from web pages autonomously.

Next-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization

Python, LlamaIndex, LangChain, 15 Property Graph, 4 RDF , 10 Vector, OpenSearch, Elasticsearch, Alfresco, Nuxeo DBs. 14 data sources (10 auto-sync), KG auto-building, Ontologies, LLMs, Docling, LlamaParse, LiteParse, GraphRAG, RAG, Hybrid Search, AI Chat. TypeScript React, Vue, Angular frontends, REST, MCP Server. Options: Langflow, CocoIndex

Rome is the agentic OS.

TypeScript multi-agent framework that runs in your own environment: consequential actions wait for approval and every run leaves a verifiable record. Describe the goal, not the graph. 13 built-in providers (Claude, OpenAI, Gemini, DeepSeek and more) plus any OpenAI-compatible endpoint, local models included.

Markdown that runs — one file, any agent.

UI over MCP. Create next-gen UI experiences with the protocol and SDK!

Implementation of Podlite markup language

Unofficial Ruby SDK for Claude Agent

Build autonomous AI agents in Python.

Semi-Structured Agentic Framework. Workflows build themselves as agents discover what needs to be done, not what you predicted upfront.

The World's First Virtual Terminal for AI Agents

Open-source control plane for your AI agents. Connect tools, hire agents, track every token and dollar