-
Notifications
You must be signed in to change notification settings - Fork 0
agentic frameworks
Nicolas Cravino edited this page Apr 13, 2026
·
9 revisions
id: agentic-frameworks title: Agentic Frameworks tags: [python, langgraph, langchain, azure, openai, mlx, audio, cli, stt, tts] created: 2026-04-11 updated: 2026-04-13 freshness: fresh
Six repositories demonstrating diverse agentic AI patterns — from a mental model visualization (Agent Stack) through workflow conversion (N8n2LangGraph), coding assistants (DeepAgent Azure CLI), voice analysis research loops (SST-AutoResearch), SAP implementation onboarding automation (ProjectPulse), and experimental multi-agent requirements generation (AutoRequirementsAgent). LangGraph and AutoGen are the two orchestration frameworks represented.
- Agent Stack decomposes agentic systems into 10 layers, reframing the LLM as a fallible component within a larger deterministic system. ^src:agent-stack
- DeepAgent Azure CLI provides a full coding agent (file R/W, shell, glob, grep, sub-agents) wired to Azure OpenAI with Textual TUI, reasoning effort control (low/medium/high), and SQLite session persistence. ^src:deepagent-azure-cli
- DeepAgent Azure CLI can run fully offline using a local MLX server that emulates the Azure OpenAI API. ^src:deepagent-azure-cli
- N8n2LangGraph converts n8n workflow JSON into standalone LangGraph Python scripts, with optional reflection loops and LLM-assisted translation for unsupported nodes. ^src:n8n2langraph
- SST-AutoResearch implements a Karpathy-style autoresearch loop where the LLM drives hypothesis → design → execute → evaluate → reflect cycles over speaker voice dynamics (Takens' embedding, Lyapunov exponents, recurrence analysis). ^src:sst-autoresearch
- ProjectPulse processes meeting recordings through a 6-phase pipeline (ingest → transcribe → analyze → wiki → podcast) with 79 integration tests, checkpoint/resume, and token budget enforcement. ^src:projectpulse
- ProjectPulse generates a full Karpathy-style interlinked wiki with per-meeting summaries, SAP Activate phase roll-ups, cross-cutting themes, stakeholder profiles, decision log, and onboarding Q&A. ^src:projectpulse
- AutoRequirementsAgent experiments with strict JSON-format inter-agent messaging and state-transition functions, using nested GroupChat with local Ollama LLMs (Nemotron 70B, Hermes 70B) for deterministic multi-agent coordination. ^src:autogen-requirements-agent
- Could N8n2LangGraph be used to convert workflows into DeepAgent Azure CLI custom tools?
- How does SST-AutoResearch's audio pipeline compare with ProjectPulse's transcription layer?
- ai-security-pentesting (Agent Stack mental model, DeepAgent Azure context)
- local-inference-mlx (SST-AutoResearch and DeepAgent use MLX backends)
- oscal-compliance (shared LangGraph patterns)
- Why Your Agentic AI Pipeline Might Not Need Code — 2026-02-11. ^src:agentic-pipeline-code-optional
- How I Automated My AI News Workflow — 2025-06-21. ^src:automated-ai-news-workflow
- The One-Person Conglomerate Is Real — 2026-03-08. ^src:one-person-conglomerate-reality
- The Best AI You'll Ever Have Unrestricted Access To — 2026-02-24. ^src:best-ai-unrestricted-access