AI

Autonomous agents

Auto-GPT — self-hosted autonomous GPT-4 agent
Hermes Agent — self-hosted agent with its own memory and skills, reachable from Telegram/Discord/Slack and cron
firstmate — one supervisor agent that runs a crew of coding agents in parallel worktrees
Orca — desktop app for running several CLI agents side by side, each in its own worktree
Open Interpreter — natural language interface for executing code
LangChain — Python framework for building LLM applications

Cognitive Debt — keeping up with agent-written code: explainers, quizzes, micro-worlds
Prompt Engineering — 3S principle, role-based prompting
SWE-bench
- Can Language Models Resolve Real-World GitHub Issues?
Latent Space | swyx & Alessio | Substack
- The AI Engineer newsletter + Top 10 US Tech podcast. Exploring AI UX, Agents, Devtools, Infra, Open Source Models.
Continue
- Create, share, and use custom AI code assistants with our open-source IDE extensions and hub of models, rules, prompts, docs, and other building blocks
Jina AI - Reader API
- Convert a URL to LLM-friendly input, by simply adding r.jina.ai in front.

uvx --from git+https://github.com/github/spec-kit.git specify init --here

claude

You will know that things are configured correctly if you see the /specify, /plan, and /tasks commands available.