📚 Tom's Notes

Search

SearchSearch

AI agents

Jun 11, 20263 min read

Access to tools

Skills or MCP ?

https://david.coffee/i-still-prefer-mcp-over-skills/

Skills

https://agentskills.io/home

Example of skill

https://github.com/retlehs/quien/blob/main/SKILL.md

Hooks

https://code.claude.com/docs/en/hooks

Software architecture

Resumable, cancellable token transport

https://zknill.io/posts/everyone-said-sse-token-streaming-was-easy/

Agent protocols

Overview of agent protocols to give access to existing systems:

https://arxiv.org/html/2504.16736v2

Model Context Protocol (MCP)

https://www.anthropic.com/news/model-context-protocol

https://modelcontextprotocol.io/

https://blog.sshh.io/p/everything-wrong-with-mcp

  • Protocol security
  • UI/UX Limitations
  • LLM Security
  • LLM Limitations

https://www.permit.io/blog/the-ultimate-guide-to-mcp-auth

  • MCP authentication

Agent to Agent (A2A) protocol

https://developers.googleblog.com/en/a2a-a-new-era-of-agent-interoperability/

Apideck CLI

https://www.apideck.com/blog/mcp-server-eating-context-window-cli-alternative#three-approaches-to-the-same-problem

Code Mode / CodeAct

Instead of direct tool calling, the agent generates code (Python scripts) to execute actions:

https://openreview.net/forum?id=jJ9BoXAfFa

https://github.com/xingyaoww/code-act

https://blog.cloudflare.com/code-mode/

Research studies

Measure of autonomy

https://www.anthropic.com/research/measuring-agent-autonomy

Effectiveness of providing context

https://arxiv.org/abs/2602.11988

  • AGENTS.md tend to be ineffective

Multi-agent configurations

https://research.google/blog/towards-a-science-of-scaling-agent-systems-when-and-why-agent-systems-work/

UX challenges

https://justin.searls.co/posts/why-agents-are-bad-pair-programmers/

Infosec challenges

First, an analysis of (in)security of MCP implementations:

https://github.com/harishsg993010/damn-vulnerable-MCP-server

And a close look at the challenges related to choice of transport (stdio vs HTTP / SSE):

https://raz.sh/blog/2025-05-02_a_critical_look_at_mcp

https://forgecode.dev/blog/prevent-attacks-on-mcp/

Tools

Claude Code

Cheatsheet:

https://cc.storyfox.cz/

How Claude Code works in large code bases:

https://claude.com/blog/how-claude-code-works-in-large-codebases-best-practices-and-where-to-start

Claude Code + OpenSeek v4

https://github.com/aattaran/deepclaude

OpenAI Codex

https://openai.com/codex/

OpenCode

https://opencode.ai/

https://github.com/anomalyco/opencode

https://jola.dev/posts/running-local-models-on-m4

Hermes Agent

https://github.com/nousresearch/hermes-agent

Pi

https://github.com/earendil-works/pi/tree/main/packages/coding-agent

zerostack

Minimalist coding agent written in Rust:

https://crates.io/crates/zerostack/1.0.0

  • efficient
  • supports multiple LLM providers
  • optional sandboxing with bubblewrap

MyManus

Open-source clone of Manus.ai:

https://github.com/emsi/MyManus/blob/master/prompts/prompt.md

OpenClaw

https://blog.nishantsoni.com/p/ive-seen-a-thousand-openclaw-deploys

  • Challenges, limited use cases
  • Long-running tasks, memory and context management

Shelley

https://github.com/boldsoftware/shelley/blob/main/ARCHITECTURE.md

Memory layer

https://extency.com/blog/markdown-versioned-folders-agent-brain-2026

https://stash.alash3al.com/

Sandbox with previews

https://github.com/tastyeffectco/sandboxes

Agent harnesses and sandboxes

https://mendral.com/blog/agent-harness-belongs-outside-sandbox

Multi-platform sandbox

https://pierce.dev/notes/a-deep-dive-on-agent-sandboxes

Nono

https://github.com/always-further/nono

  • Linux and Mac
  • Designed for agent sandboxing
  • flexible profiles

With high-quality Python bindings:

https://github.com/always-further/nono-py

Zeroboot

https://github.com/adammiribyan/zeroboot

Lima VM

https://www.metachris.dev/2025/11/sandbox-your-ai-dev-tools-a-practical-guide-for-vms-and-lima/#lima-vm-introduction

Bubblewrap

https://github.com/containers/bubblewrap

Jai

https://jai.scs.stanford.edu/

Micro sandbox tor MCP

https://github.com/microsandbox/microsandbox

Terragon

To manage the work of multiple agents:

https://ymichael.com/2025/07/15/claude-code-unleashed.html

Provides seamless transition from background agents (running in the cloud) to local runs.

Details on the value of Claude Code

https://github.com/MinishLab/semble

Hands-on projects

Build an agent for long task planning

https://medium.com/@rogi23696/build-a-basic-ai-agent-from-scratch-long-task-planning-14e803f9bd6d

Code review agent with OpenCode

https://martinalderson.com/posts/using-opencode-in-cicd-for-ai-pull-request-reviews/

Developing with GH Copilot Agent Mode

https://austen.info/blog/github-copilot-agent-mcp/

Coding agent in Go

https://github.com/ghuntley/how-to-build-a-coding-agent

Agent to support investment decisions

https://github.com/lastmile-ai/mcp-agent/tree/main/examples/usecases/mcp_realtor_agent

To analyze huge amounts of logs

https://mendral.com/blog/frontier-model-lower-costs

  • Low-cost model as triager
  • Vector search
  • Frontier model for analysis on subset

Building an agent / Harness engineering

https://sketch.dev/blog/agent-loop

https://ampcode.com/how-to-build-an-agent

Internals of Claude Code

https://x.com/AlphaSignalAI/status/2039360361632326003?utm_source=alphasignal&utm_campaign=6c0a1b85a97c6485&lid=Rf2sdXOArrLYNFsZ

APIs called from LLMs

Stripe

https://docs.stripe.com/building-with-llms

Tool calling

https://jngiam.bearblog.dev/mcp-large-data/

MCP + ollama

https://www.polarsparc.com/xhtml/MCP.html

Agent Development Kit (ADK)

https://developers.googleblog.com/en/agent-development-kit-easy-to-build-multi-agent-applications

12-factor agents

https://github.com/humanlayer/12-factor-agents

Ecosysyem

Large list of available MCP servers

https://github.com/modelcontextprotocol/servers

Research

Self-improving agents

Darwin Goedel Machines (DGMs)

https://arxiv.org/abs/2505.22954

https://richardcsuwandi.github.io/blog/2025/dgm/

See also

Graph View

Backlinks

  • No backlinks found