Skillget

tutorials

mcp
Security Audit
Warn
Health Warn
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 7 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

One‑stop library of Regolo.ai’s blog tutorials. Curated, up‑to‑date, and ready to use.

README.md

Regolo Labs tutorials for AI agents, RAG and LLM inference

Python 3.10+ Code: runnable examples OpenAI-compatible API MCP ready License: MIT

Runnable playbooks for building AI agents, retrieval-augmented generation (RAG), MCP tools and LLM evaluation on Regolo.ai. Regolo serves open-weight models such as Qwen, GLM, Gemma and gpt-oss through an OpenAI-compatible API, hosted in European data centers. Each folder includes working code, setup notes and a companion article on regolo.ai.

[!IMPORTANT]

Get 30 days free and 70% off for 3 months

Every tutorial needs an API key. Sign up on Regolo to get 30 days completely free, plus a 70% discount for the following 3 months.

🚀 Start your free trial on regolo.ai 🚀

Explore Regolo: Platform | Models library | Docs and guides | YouTube | Discord

Why Regolo

  • OpenAI-compatible. Point your existing OpenAI SDK at https://api.regolo.ai/v1 and keep your code.
  • Open-weight models. Choose the right model for each task, from compact models to the 122B-parameter Qwen 3.5 used in several tutorials.
  • European hosting. Zero Data Retention in EU data centers, powered by renewable energy.
  • Pay as you go or a flat plan. Start with pay-as-you-go pricing, then compare it with the Core subscription as your usage grows.

Get started in three steps

  1. Clone the repository: git clone https://github.com/regolo-ai/tutorials.git
  2. Open a tutorial folder and read its README.md.
  3. Get a free API key on regolo.ai/pricing, export it as REGOLO_API_KEY, and run the code.

Tutorials

Tutorial Description Labels Article link
Private long-term memory for coding agents Cognitive long-term memory framework with Cognee Knowledge Graph, vector store, ReAct self-healing loop, and Regolo Zero Data Retention. Python · Runnable · GPU 100% Ready Read article
Closed-loop: self-correcting AI code reviewer Self-correcting AI code reviews with dual-gate verification, Qdrant semantic memory, cross-encoder reranking, and persistent skill accumulation. Python · Runnable · GPU 100% Ready Read article
Self-improving secure coding loop Memory-augmented secure coding agent with Open SWE, Deepsec verification, Cognee Knowledge Graph, and Regolo GLM-5.2. Python · Runnable · GPU 100% Ready Read article
Deep agents: tool synthesis with Brick routing Autonomous multi-agent framework with dynamic DAG planning and Brick semantic complexity routing on Regolo.ai. Python · Runnable · GPU 100% Ready —
Clawdbot knowledge base Internal knowledge bot with hybrid retrieval (embeddings, BM25 and reranker) and a Telegram interface. Python · Runnable · GPU 100% Ready Read article
CrewAI product launch campaign Automated product launch system with a crewAI multi-agent workflow and Regolo infrastructure. Python · Runnable · GPU 100% Ready Read article
Cheshire Cat AI and Regolo: enterprise AI agent setup Enterprise-ready AI agent setup via an OpenAI-compatible API and open models. Python · Runnable · GPU 100% Ready Read article
Build faster: LLM as a service with Qwen 3.5 122B Practical LLM-as-a-service patterns for developers: boilerplate generation, a streaming assistant, lightweight RAG, and structured extraction. Python · Runnable · GPU 100% Ready Read article
Orchestrating predictable AI agents with Parlant and Regolo Deterministic policy orchestration with a Parlant-style control layer and a Regolo backend. Python · Runnable · GPU 100% Ready Read article
Advanced RAG in 2026: long context is not memory Enterprise ticket triage that uses Regolo for structured incident analysis, escalation, and mitigation planning. Python · Runnable · Enterprise triage Read article
Programmatic tool calling on Regolo GPUs Build smarter agents with classic JSON tool calling and programmatic tool calling, using a restricted runtime and multi-step orchestration. Python · Runnable · GPU 100% Ready Read article
Production-ready RAG on open models End-to-end production RAG: chunking, retrieval, reranking, evaluation, and optimization. Python · Runnable · GPU 100% Ready Read article
Build a hybrid inference stack without sacrificing quality Regolo-only incident triage demo with coloured logs, local .env loading, and structured JSON responses. Python · Runnable · Logging Read article
LLM architectures in 2026: optimize for what matters, not benchmarks A lightweight architecture router that loads .env, reads REGOLO_CORE_MODEL, and selects a Regolo model before sending the request. Python · Runnable · Model routing Read article
AI agents and tool chaining in 2026 Contract-review workflow that chains extraction, reranking, and policy decisions into one runnable script. Python · Runnable · Workflow Read article
How to build a PR review assistant Automated PR review assistant that reads local .env settings, picks a model, and reviews Git diffs through Regolo. Python · Runnable · Code review Read article
AI governance and copyright policy gateway Policy gateway example with PII removal, BLOCK, ALLOW and TRANSFORM classification, and two-stage compliance. Python · Runnable · Governance Read article
OpenClaw vs Hermes Agent memory benchmark Direct comparison between Hermes Agent and OpenClaw, measuring local RAM, disk, and recall latency on a Regolo backend. Python · Runnable · Agent memory Read article
TurboQuant outperforms traditional KV quantization Official benchmark comparing TurboQuant to classic scalar KV quantization for LLMs. Measures accuracy, bias, KL divergence, and speed. Python · Benchmark · Quantization Read article
Run MiroFish with regolo.ai: a complete integration guide Walks you through every step: cloning MiroFish, configuring it to point at regolo.ai, running your first simulation, and tuning for performance. Python · Runnable · GPU 100% Ready Read article
Accelerate LLM inference with DFlash speculative decoding Train and serve a DFlash block-diffusion speculator with vLLM. Generates up to 15 candidate tokens in one parallel forward pass for 3–5× throughput gains with lossless output. Python · vLLM · GPU 100% Ready Read article
Context-engineered agent Compact demo of context engineering for long-horizon agents: just-in-time data ingestion, active compaction, structured external memory, and sub-agent isolation, without prompt stuffing. Python · Runnable · Ollama compatible Read article
Context engineering for agents 101: harness kit for OpenCode, Claude Code and Codex Four runnable modules and an MCP server: progressive skill disclosure, retrieve-offload-delegate, reversible compaction with cache-safe memory, and a long-running harness with an independent evaluator. Measured token savings included. Python · MCP · Runnable · Context engineering Read article
Stateful agent memory and dreaming pipeline Three-layer memory architecture inspired by Anthropic's memory system. Decouples live runtime execution from background database consolidation. Supports Ollama and Regolo backends. Python · Runnable · Agent memory Read article
StockPilot: decomposed AI agent in the Anthropic workshop style Inventory management agent that routes queries to specialized subagents and code-execution tools. Implements the decomposed agent pattern with skill-specific context injection and verifiable results. Python · Runnable · GPU 100% Ready —
Regolo Eval Studio: evaluate open-weight models with Langfuse Local web studio that benchmarks open-weight models on your own dataset, compares PAYG and Core costs, streams traces to Langfuse, and generates a GitHub Actions faithfulness gate. Python · Langfuse · LLM evaluation Read article
SearXNG private research scraper Private web research agent fleet with a SearXNG search backend, intent-orchestrated six-worker subagent query expansion, topic relevance filtering, spatial chunking, and grounded synthesis on Regolo.ai. Python · Runnable · GPU 100% Ready Read article

Contributing

Contributions are welcome: new tutorials, fixes and clearer explanations. Open an issue or a pull request, and follow the folder structure of the existing tutorials, with a README.md in each one.

Links

License

MIT. See LICENSE for details.

Powered by

  • Regolo.ai: Zero Data Retention in EU data centers, powered by 100% green, carbon-free energy. OpenAI-compatible LLM API.

Reviews (0)

No results found