Open-source decision intelligence

Find the right software to build anything.

Describe what you want to build. ThingsO helps you discover relevant projects, understand their health and trade-offs, compare alternatives, and move toward an implementation plan.

Decision first

Not another repository directory.

ThingsO separates source facts from interpretation and optimizes for fit-by-use-case rather than raw popularity.

DiscoverSearch by what you want to accomplish.
AnalyzeSee factual health signals and evidence-backed interpretation.
CompareEvaluate alternatives against the same decision criteria.
BuildTurn a selected stack into reviewed Build Ideas and blueprints.

Source-backed dataset

Repository intelligence

Explore discovery →

NousResearch

hermes-agent

76Health
AI inference

Hermes Agent is a personal AI agent platform built around persistent memory, skills learned from experience, tool use and access through multiple interfaces. The project supports a CLI/TUI, messaging gateways, scheduled tasks, MCP integration, browser and terminal tools, multiple model providers and self-hosted operation. Its differentiator is the long-lived personal-agent model: retaining useful context and procedural skills across sessions rather than treating every run as a stateless request.

235.3KPythonMITai-agentclicloud-hosteddesktopdeveloper-productivitylocal

n8n-io

n8n

79Health
Source fact

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

202.2KTypeScriptNOASSERTIONworkflow-automation

ollama

ollama

82Health
Source fact

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

179.3KGoMITllm-serving

firecrawl

firecrawl

79Health
Source fact

The context API to search, scrape, and interact with the web at scale. 🔥

171.5KTypeScriptAGPL-3.0web-scraping

huggingface

transformers

82Health
Source fact

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

164.4KPythonApache-2.0llm-serving

langgenius

dify

79Health
Source fact

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

153.3KTypeScriptNOASSERTIONai-agent