ai-agent-book vs letta
ai-agent-book is an open-source hosted agent for knowledge and memory. letta is an open-source agent framework for knowledge and memory.
- ai-agent-book has more GitHub stars (58,395 vs 25,466).
- ai-agent-book is best for learning agent design principles.
- letta is best for run a coding agent that remembers a project.
- What it is
- ai-agent-book is an open-source hosted agent for knowledge and memory.letta is an open-source agent framework for knowledge and memory.
- Best for
- Learning agent design principlesRun a coding agent that remembers a project
- Kind
- AgentAgent
- Pricing
- Open sourceOpen source
- Platforms
- WebCLI, Web, Slack, telegram, discord, self-hosted, API
- Agent type
- Hosted agentAgent framework
- GitHub stars
- 58.4K25.5K
- Last commit
- Oct 2026Oct 2026
- License
- Apache-2.0Apache-2.0
- Open source
- Good for
- Learning agent design principles; Running hands-on agent experiments; Teaching an agent engineering courseRun a coding agent that remembers a project; Add an AI coworker to Slack; Automate recurring work on a schedule
What ai-agent-book does
10-chapter book
Covers agents from principles to engineering.
109 experiments
Companion code projects to run.
Multiple formats
PDF, EPUB and online reading.
15 languages
Original Chinese plus community translations.
What letta does
Stateful agents
Agents carry memory and learn over time.
Letta Code CLI
Open-source harness for coding and assistant work.
Skills and Schedules
Reusable workflows and recurring prompts.
Channels
Slack, Telegram and Discord integrations.
Agent SDK
Embed stateful agents in applications.
Cloud or self-run
Letta Cloud or the App Server.
ai-agent-book vs letta: questions
Is ai-agent-book or letta cheaper?
Both are open source. Compare current plans on each official site.
What is the difference between ai-agent-book and letta?
ai-agent-book is an open-source hosted agent for knowledge and memory. letta is an open-source agent framework for knowledge and memory. ai-agent-book has more GitHub stars (58,395 vs 25,466).

