simply for the love of the game
San Francisco, CA
Joined June 2023
- Tweets647
- Following341
- Followers1.6K
- Likes2.1K
Pinned Tweet
I’ve been building with LLMs since my first startup in 2022, and for years I waited on the sidelines for someone to solve memory.
Nobody did, so I spent the last 4 months building it: a shared learning layer that gives every agent on your team the context your best engineer carries around. Today we’re opening it to everyone: Glen
• 21% faster to a merged change while using 1/3 fewer tokens.
• One agent learns something, every agent on your team knows it (harness agnostic, cross teammate)
First 15,000 memories are free, we are building the shortest path to a truly compounding org.
Nikos retweeted
Glen is an amazing product, couldn't imagine working without it now
I’ve been building with LLMs since my first startup in 2022, and for years I waited on the sidelines for someone to solve memory.
Nobody did, so I spent the last 4 months building it: a shared learning layer that gives every agent on your team the context your best engineer carries around. Today we’re opening it to everyone: Glen
• 21% faster to a merged change while using 1/3 fewer tokens.
• One agent learns something, every agent on your team knows it (harness agnostic, cross teammate)
First 15,000 memories are free, we are building the shortest path to a truly compounding org.
Nikos retweeted
heavily recommend
I’ve been building with LLMs since my first startup in 2022, and for years I waited on the sidelines for someone to solve memory.
Nobody did, so I spent the last 4 months building it: a shared learning layer that gives every agent on your team the context your best engineer carries around. Today we’re opening it to everyone: Glen
• 21% faster to a merged change while using 1/3 fewer tokens.
• One agent learns something, every agent on your team knows it (harness agnostic, cross teammate)
First 15,000 memories are free, we are building the shortest path to a truly compounding org.
Nikos retweeted
Memory is the bottleneck. not hbm, but agent memory. Not many people are talking about it, Glen is the best dev tool to solve it.
I’ve been building with LLMs since my first startup in 2022, and for years I waited on the sidelines for someone to solve memory.
Nobody did, so I spent the last 4 months building it: a shared learning layer that gives every agent on your team the context your best engineer carries around. Today we’re opening it to everyone: Glen
• 21% faster to a merged change while using 1/3 fewer tokens.
• One agent learns something, every agent on your team knows it (harness agnostic, cross teammate)
First 15,000 memories are free, we are building the shortest path to a truly compounding org.
Nikos retweeted
I've been using Glen for months and its been an insane unlock for me and my team. Go try it out!
I’ve been building with LLMs since my first startup in 2022, and for years I waited on the sidelines for someone to solve memory.
Nobody did, so I spent the last 4 months building it: a shared learning layer that gives every agent on your team the context your best engineer carries around. Today we’re opening it to everyone: Glen
• 21% faster to a merged change while using 1/3 fewer tokens.
• One agent learns something, every agent on your team knows it (harness agnostic, cross teammate)
First 15,000 memories are free, we are building the shortest path to a truly compounding org.
Nikos retweeted
I use @try_glen and it is quite good!
I’ve been building with LLMs since my first startup in 2022, and for years I waited on the sidelines for someone to solve memory.
Nobody did, so I spent the last 4 months building it: a shared learning layer that gives every agent on your team the context your best engineer carries around. Today we’re opening it to everyone: Glen
• 21% faster to a merged change while using 1/3 fewer tokens.
• One agent learns something, every agent on your team knows it (harness agnostic, cross teammate)
First 15,000 memories are free, we are building the shortest path to a truly compounding org.
Nikos retweeted
We've been using Glen to share memories between our developers and our background/autonomous agents for a while and it's made all of us better, faster, and the agents are cheaper (I still cost the same).
I’ve been building with LLMs since my first startup in 2022, and for years I waited on the sidelines for someone to solve memory.
Nobody did, so I spent the last 4 months building it: a shared learning layer that gives every agent on your team the context your best engineer carries around. Today we’re opening it to everyone: Glen
• 21% faster to a merged change while using 1/3 fewer tokens.
• One agent learns something, every agent on your team knows it (harness agnostic, cross teammate)
First 15,000 memories are free, we are building the shortest path to a truly compounding org.
Nikos retweeted
the biggest bottleneck in engineering has become context. we are constantly re-teaching our agents how to work within our teams/repos/projects.
my team and i have been using @try_glen for months and it has become core to how we ship faster and higher quality work!
congratulations to the team on the launch!!
I’ve been building with LLMs since my first startup in 2022, and for years I waited on the sidelines for someone to solve memory.
Nobody did, so I spent the last 4 months building it: a shared learning layer that gives every agent on your team the context your best engineer carries around. Today we’re opening it to everyone: Glen
• 21% faster to a merged change while using 1/3 fewer tokens.
• One agent learns something, every agent on your team knows it (harness agnostic, cross teammate)
First 15,000 memories are free, we are building the shortest path to a truly compounding org.
2.
When a request touches past work, Glen searches team memory and drops the relevant context into the session while the agent works, gently steering it to better outcomes from the sidelines. Every recalled answer shows where it came from, when, and who.
3. Glen only reads what your team already shares, like public Slack channels and team-visible transcripts. It skips DMs, private channels and private recordings. Secrets and personal data are redacted before anything is stored. Glen incognito lets you use team memory without adding your own session to it. Glen also works totally single player, so don’t hesitate to try it solo before onboarding the rest of your team!
Nikos retweeted
Name a good startup not on Glen. @nikos1
I’ve been building with LLMs since my first startup in 2022, and for years I waited on the sidelines for someone to solve memory.
Nobody did, so I spent the last 4 months building it: a shared learning layer that gives every agent on your team the context your best engineer carries around. Today we’re opening it to everyone: Glen
• 21% faster to a merged change while using 1/3 fewer tokens.
• One agent learns something, every agent on your team knows it (harness agnostic, cross teammate)
First 15,000 memories are free, we are building the shortest path to a truly compounding org.
Nikos retweeted
the efficiency savings are super impressive
I’ve been building with LLMs since my first startup in 2022, and for years I waited on the sidelines for someone to solve memory.
Nobody did, so I spent the last 4 months building it: a shared learning layer that gives every agent on your team the context your best engineer carries around. Today we’re opening it to everyone: Glen
• 21% faster to a merged change while using 1/3 fewer tokens.
• One agent learns something, every agent on your team knows it (harness agnostic, cross teammate)
First 15,000 memories are free, we are building the shortest path to a truly compounding org.
Nikos retweeted
unironically some unique stuff here, super excited about what @try_glen is cooking
I’ve been building with LLMs since my first startup in 2022, and for years I waited on the sidelines for someone to solve memory.
Nobody did, so I spent the last 4 months building it: a shared learning layer that gives every agent on your team the context your best engineer carries around. Today we’re opening it to everyone: Glen
• 21% faster to a merged change while using 1/3 fewer tokens.
• One agent learns something, every agent on your team knows it (harness agnostic, cross teammate)
First 15,000 memories are free, we are building the shortest path to a truly compounding org.
Nikos retweeted
Glen has been amazing to use for the past few months! Excited to see it roll out to everyone 🚀
I’ve been building with LLMs since my first startup in 2022, and for years I waited on the sidelines for someone to solve memory.
Nobody did, so I spent the last 4 months building it: a shared learning layer that gives every agent on your team the context your best engineer carries around. Today we’re opening it to everyone: Glen
• 21% faster to a merged change while using 1/3 fewer tokens.
• One agent learns something, every agent on your team knows it (harness agnostic, cross teammate)
First 15,000 memories are free, we are building the shortest path to a truly compounding org.
Visit tryglen.com to see Glen in action!
Give it a look
I’ve been building with LLMs since my first startup in 2022, and for years I waited on the sidelines for someone to solve memory.
Nobody did, so I spent the last 4 months building it: a shared learning layer that gives every agent on your team the context your best engineer carries around. Today we’re opening it to everyone: Glen
• 21% faster to a merged change while using 1/3 fewer tokens.
• One agent learns something, every agent on your team knows it (harness agnostic, cross teammate)
First 15,000 memories are free, we are building the shortest path to a truly compounding org.
Nikos retweeted
GPT-6 Astra can now paint the Golden Gate bridge and type on a keyboard. But can it throw a dinner party for real guests?
@claireymao and I are on a mission to find out. We gave it a robot arm (named Podrick) and a kitchen. As a first task, Podrick, controlled by Astra, garnishes each cup of water with a slice of lemon! 🍋
Nikos retweeted
We’re giving away $1 million to agents.
Introducing Composio Instant: the easiest way for agents to pay for their own tools.
Claim your agent's share: composio.dev/instant