Skills are used to expand an agent's capabilities -- agents can go "load" a specialty, much like how Neo learns kung fu.
This is a big step. Skills are an important way to expand procedural memory for agents.
🧵
Skills are used to expand an agent's capabilities -- agents can go "load" a specialty, much like how Neo learns kung fu.
This is a big step. Skills are an important way to expand procedural memory for agents.
🧵
(thread coming soon on Agent Skills, Anthropic's open standard for skills)
agentskills.io/home
(thread coming soon on Agent Skills, Anthropic's open standard for skills)
agentskills.io/home
Join our Discord to learn about what's new in Letta, ask questions, and provide feedback.
If you are not already in the Discord, join us: discord.gg/letta
Join our Discord to learn about what's new in Letta, ask questions, and provide feedback.
If you are not already in the Discord, join us: discord.gg/letta
📦 letta-ai / letta
⭐ 19,697 (+102)
🗒 Python
Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.
- open source (apache 2.0)
- model agnostic
- portable agent learning and memory
L: https://www.letta.com/blog/letta-code
C: https://news.ycombinator.com/item?id=46294274
posted on 2025.12.16 at 15:51:27 (c=0, p=4)
L: https://www.letta.com/blog/letta-code
C: https://news.ycombinator.com/item?id=46294274
posted on 2025.12.16 at 15:51:27 (c=0, p=4)
Note though that going through us directly is probably a better idea if you want good agents. We charge per message, not per token.
Note though that going through us directly is probably a better idea if you want good agents. We charge per message, not per token.
One agent per project, specialized, infinitely lived.
No more compactions, no more forgetting.
- open source (apache 2.0)
- model agnostic
- portable agent learning and memory
One agent per project, specialized, infinitely lived.
No more compactions, no more forgetting.