Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

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.

An enterprise AI development framework for building AI agents. It provides unified management of multi-provider LLMs, secure enterprise knowledge bases with high-precision retrieval, visual workflow orchestration and multi-agent coordination. Compatible with mainstream Agent Skill standards, it enables developers to efficiently build production-gra

Python toolkit, MCP server, and agent skills for reproducible, auditable clickstream and event log analytics. Helps AI agents, data scientists and analysts build, validate, and cross-check product analytics, quantitative UX, customer journeys, graph-based user flows, behavioral segmentation, A/B tests, process mining models, Markov chain simulation

Open-source Agent Operating System

🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.

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

Universal memory runtime for AI agents

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

Pixelize the real world on-chain

Turn scattered knowledge, operational data, and history into source-linked context that your agents can inspect, explain, and reuse.

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

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

A framework for discovering, compiling, and validating reusable skills for scientific agents.

🦖 Serverless AI Agent Framework with Geo-distributed Edge AI Infra.

The AI Operating System for Delphi. 100% native framework with RAG 2.0, autonomous agents, MCP protocol, and universal LLM connector. Supports OpenAI, Claude, Gemini, Ollama, and more. Delphi 10.4+ (limited), full support from Delphi 12 Athens.

Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift

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

Open source version of Claude Managed Agents. Fastest way to build and deploy reliable AI agents, MCP tools and agent-to-agent.

AI said it finished. Flyto2 shows the proof.

Poirot is a deep research agent kernel built for those who care about how agents are architected.