Rui CarmoNotes and resources on building and operating agentic AI systems, covering orchestration frameworks, task routing, memory, and evaluation approaches that extend baseline LLM capabilities.
Resources
| Field | Category | Date | Link | Notes |
|---|---|---|---|---|
| Tools | 2026 | beads | a distributed, git-backed issue tracker that provides structured memory for AI agents. |
|
| Agent Frameworks | Frameworks | 2025 | FlashLearn | a simple interface for incorporating Agent LLMs |
| agno | a lightweight library for building Multimodal Agents |
|||
| crewAI | framework for orchestrating role-playing, autonomous AI agents (multi-agent automation) |
|||
| AgentKit | build multi-agent networks in TypeScript with deterministic routing and rich tooling via MCP |
|||
| Agent Framework | Microsoft open-source agentic framework |
|||
| Agent Memory | Tools | 2026 | claude-mem | a persistent memory compression system for Claude Code with search tools |
| 2025 | AgenticMemory | a tool for creating and managing memory in LLMs |
||
| letta | a tool for creating and managing memory-backed agents |
|||
| Agent Platforms | Platform | HelixML | an interesting enterprise-grade agentic platform with tools for integration and observability |
|
| Sim | open-source platform to build and deploy AI agent workflows |
|||
| Agent Systems | Frameworks | pixelagent | an agent engineering blueprint |
|
| 2024 | pipecat | yet another LLM agent framework |
||
| Samples | TinyTroupe | a multiagent persona simulation |
||
| Tools | 2026 | nanoclaw | A minimalist agent that runs inside Apple’s container framework |
|
| 2025 | R2R | production-ready AI retrieval system for agentic RAG via a REST API |
||
| 2024 | plandex | yet another long-running agent tool for complex coding tasks |
||
| 2023 | Auto-GPT | an attempt to provide ChatGPT with a degree of autonomy |
||
| Code Agents | Samples | 2025 | amplifier | a technology demonstrater for agentic coding |
| 2024 | devlooper | a program synthesis agent that autonomously fixes its output by running tests |
||
| Tools | 2026 | kimi-cli | CLI tool for interacting with the Kimi AI assistant |
|
| pi-mono | a coding agent and toolkit for building and managing LLM-driven agents and deployments. |
|||
| Codex CLI | OpenAI’s lightweight agentic coding CLI for the terminal |
|||
| 2025 | Toad | a unified terminal UI to run coding agents via ACP |
||
| goose | a local AI agent focused on development tasks |
|||
| quibbler | a critic for coding agents that can also work as an MCP |
|||
| mistral-vibe | Mistral’s agentic coding CLI |
|||
| Development Resources | References | 2026 | Context7 | a curated database of context for several development stacks |
| Memory Systems | Tools | 2025 | beads | a memory system experiment for LLM agents |
| Ontologies | Frameworks | firm | an ontology framework for structuring agent knowledge about businesses |
|
| Personal Assistants | Tools | 2026 | OpenClaw | A personal, always-on assistant framework that has become a sort of cultural phenomenon. Amazingly insecure by design, with a strong community and ecosystem around personal agent deployment. |
| Research Agents | Samples | 2025 | STORM | LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations |
| 2023 | gpt-researcher | a simple agent that does online research on any given topic |
||
| Sandboxing Environments | Tools | 2026 | amla-sandbox | A WASM-based sandbox with capability enforcement for running agent-generated code safely. Provides isolation without Docker and reduces tool-call overhead. |
| yolobox | a containerized sandbox for running AI coding agents safely |
|||
| Cua | A sandboxing toolkit and agentic platform for running agents in isolated environments. Covers Docker, QEMU, and Apple Virtualization for benchmarking, safe code execution, and UI automation. |