The AI agent stack
Autonomous agents plan, call tools, and act over multiple steps. The stack pairs an agent runtime with model tooling, integration glue, and tracing.
GraphCanon updated 5d · 64 views this month
Agent runtime - planning, tool use, and multi-step control flow.
When not to use: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism.
hermes-agent
NousResearch/hermes-agent
The agent that grows with you
ECC
affaan-m/ECC
The agent harness performance optimization system for AI agents
AutoGPT
Significant-Gravitas/AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on.
dify
langgenius/dify
Production-ready platform for agentic workflow development
Framework & tooling - prompt/state management and RAG the agent can call.
When not to use: Skip the framework layer if your agent only needs one or two hardcoded tools.
AutoGPT
Significant-Gravitas/AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on.
transformers
huggingface/transformers
Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models
tensorflow
tensorflow/tensorflow
An Open Source Machine Learning Framework for Everyone
prompts.chat
f/prompts.chat
Share, discover, and collect prompts from the community
Gateways & SDKs - route across model providers and expose tools (e.g. via MCP).
When not to use: A gateway is overkill when you're pinned to a single provider and model.
ECC
affaan-m/ECC
The agent harness performance optimization system for AI agents
prompts.chat
f/prompts.chat
Share, discover, and collect prompts from the community
OpenHands
OpenHands/OpenHands
AI-Driven Development
Flowise
FlowiseAI/Flowise
Build AI Agents, Visually
Tracing - see every step, tool call, and token so failures are debuggable.
When not to use: There is no good reason to run agents in production without tracing.
generative-ai-for-beginners
microsoft/generative-ai-for-beginners
21 Lessons for Getting Started with Generative AI
headroom
headroomlabs-ai/headroom
Compress tool outputs and data to reduce tokens before reaching the LLM.
CL4R1T4S
elder-plinius/CL4R1T4S
Leaked system prompts for various AI agents include ChatGPT, Claude, Gemini among others emphasizing transparency and access.
LibreChat
danny-avila/LibreChat
Enhanced ChatGPT Clone with extensive features and integrations for self-hosting
Common questions
- What is the the ai agent stack?
- Autonomous agents plan, call tools, and act over multiple steps. The stack pairs an agent runtime with model tooling, integration glue, and tracing.
- When should I use the the ai agent stack?
- Use this stack when your constraints match its layers: AI Agents, LLM Frameworks, Developer Tools, Evaluation & Observability. Each step on the page includes when-not-to-use guidance so you do not over-engineer.
- How does GraphCanon pick tools for the ai agent stack?
- Stack pages are editorial workflows over canonical categories. Representative tools are pulled live from the graph at render time (top adoption in each category), not a fixed marketing list.
- Where can I compare tools in this stack?
- Follow category hubs and head-to-head compare pages linked from each step. Featured comparisons cover the highest-intent pairs (frameworks, vector DBs, agent runtimes). Start at compare hub.
- Is there a machine-readable version of The AI agent stack?
- Yes. Append
.mdto `/stacks/autonomous-agent` or fetch `/md/stacks/autonomous-agent` for a markdown twin with steps, when-not notes, and tool links.