Jinja agents

Ansible role for Datadog Agent

This repo contains the critical chat_template.jinja fix for Qwen3/3.5/3.6 to work smoothly in agentic task.

mcp server for slidev to make web ppt quickly and elegantly

Easily convert agents and orchestrators from existing agent frameworks to A2A servers

Meta-specification framework for AI Agents to generate Spec-driven X toolkits automatically.

Generate production-ready Python and AI stacks by combining frameworks, data engines, tooling, and cloud deployment.

Open-science computational astronomy built to be reproduced. We pursue discovery-oriented research on modern spectroscopic surveys and publish the entire research lab, infrastructure included, as code.

Self-host Supabase in production, AI-ready: read-only MCP for your coding agent with zero secret exposure, SSO, PITR backups, monitoring, disk encryption, and one-command migration off Supabase Cloud.

Forge your own agent harness — a config-to-code generator that renders a thin, standalone Python agent harness you fully own. No LangChain/LangGraph/ADK lock-in, no dependency on the generator after generation.

Set up a modern LLM app by running one command

MoziAI-35B: Local open-source financial AI LLM. 35B MoE model compressed to 15.5GB via MoziSmartBit quantization. 256K context, vision, tool calling, 140+ tok/s on consumer GPU. Based on Qwen3.6-35B-A3B.

A python CLI tool that bootstraps production-ready GEN AI project structures with best practices and modular organization out-of-the-box

MoziAI-35B: Local open-source financial AI LLM. 35B MoE model compressed to 15.5GB via MoziSmartBit quantization. 256K context, vision, tool calling, 140+ tok/s on consumer GPU. Based on Qwen3.6-35B-A3B.

A framework for agentic AI software engineering workspaces

Field-tested local AI stack optimizations for HermesAgent, LM Studio, and Qwen 3 models

Sample Helmsman skills (MiniJinja/Jinja templates). Not production-ready.