Highlights
- Pro
Lists (1)
Stars
Knowledge Graphs for Data Interoperability with Chimera (KG4DI)
A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-writ…
The YAML Observation Data Archive & exchange (YODA) File Format
Trace origins, shared sources, and contamination risk
NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.
A collection of demos on maplib, showing different capabilities.
Post-training with Tinker
Open-source observability tool that uses AI agents to self-heal your software
A flexible and high-performance training framework designed for large-scale foundation model training on AMD GPUs
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
Instella MoE is a fully open state-of-the-art Mixture-of-Experts language model, trained end-to-end on AMD Instinct™ GPUs.
The missing open-source Kubernetes UI with a built-in MCP server for AI agents. See what's broken, why, and what changed. Issues, Topology, event timeline, Helm, GitOps, live service traffic, and c…
A collection of "git for data" snippets, models, resources
There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable an…
Programming challenges for interviewing with Didomi
BusinessLogicMesh would like to be a new way to abstract, define and use portable and governable Business logic applied to dataMesh principles
Python actor framework for heterogeneous computing.
An Agent with Semantic Memory. This is an experiment for Neuro-Symbolic AI
GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ dat…
Queryable, Datahike-backed version control with Git compatibility
Versioned, fast, distributed Datalog engine for everyone.
Scripts, configs and documentation for the pre- and midtraining activities of the Soofi Project.