←
Glen20 posts
Glen avatar

Glen

@try_glen

Shared learning for all AI agents in your org

◷ Joined April 2026
Glen avatar
Glen@try_glen·Nov 12

Today we release Cloud Skills in Glen. Cloud Skills are shared team-wide, cross harness, and are surfaced automatically as Glen detects the skill is relevant to the work you’re doing.

Nikos@nikos1Nov 12

Sending skill.md files over Slack sucks. So does uploading them to some repo no one will ever check. The average company loses tons of productivity redoing things that already exist, because people don’t know that someone on their team has curated a skill file that does the thing 10x better. Skills shouldn’t be local to one persons machine. Teammates shouldn’t need to know which skills exist: the right ones should just surface as work happens across their agents. Today we’re releasing Cloud Skills in Glen.

0:46
Glen avatar
Glen@try_glen·Nov 17

We just killed local skills.

Nikos@nikos1Nov 17

The way teams share skills today sucks. They end up scattered across teammates’ laptops, Slack threads and GitHub repos, because until now there hasn’t been a better way to share them. You don’t need another passive, shared place to put them. You need the right skill to show up in any agent when anyone on your team is doing relevant work, without them having know it exists or have it stored locally. This is why we just added Cloud Skills to Glen.

0:50
Nikos avatar
⟳ Glen retweeted
Nikos@nikos1·Nov 16

Big announcement coming. We're shooting it on the same cameras used for You Can See Everything. @shortscut team is hands down the best to ever do it.

Post attachmentPost attachment
Nikos avatar
⟳ Glen retweeted
Nikos@nikos1·Nov 13

With just a CLI command, you can actually do a transcript takeover from Claude Code to Codex, or Codex to Pi, or most harnesses to most harnesses, using Glen (tryglen.com). It also works on your teammates' transcripts, and they can take over your sessions midway in a totally different harness than what you started in. All your transcripts are also stored in the cloud. You should give it a look. It's totally free.

Nikos avatar
⟳ Glen retweeted
Nikos@nikos1·Nov 12

We built Glen around recording the sessions themselves rather than maintaining notes. When your agent needs to maintain notes on its own, it forgets to write tons of valuable things, and the setup lacks predictability in terms of what is written. You're also giving it a totally different task to do in parallel while you're asking it to do its actual work, and so we found that you can generally experience performance degradation (think more tokens, slower task completion, for worse task completion rate) from this. Glen pulls relevant context into the next session as your agent works, including stuff a teammate's agent already figured out without your agent needing to know that it should search. Might be interesting for your setup.

Nikos avatar
⟳ Glen retweeted
Nikos@nikos1·Nov 12

Sending skill.md files over Slack sucks. So does uploading them to some repo no one will ever check. The average company loses tons of productivity redoing things that already exist, because people don’t know that someone on their team has curated a skill file that does the thing 10x better. Skills shouldn’t be local to one persons machine. Teammates shouldn’t need to know which skills exist: the right ones should just surface as work happens across their agents. Today we’re releasing Cloud Skills in Glen.

0:46
Nikos avatar
⟳ Glen retweeted
Nikos@nikos1·Nov 10

name a better duo: Claude Code + Glen

Tri avatar
⟳ Glen retweeted
Tri@TridhatriV·Oct 31

The tool is called @try_glen btw

eventually, i think agents will have a tool called “ask_user_brain” this tool directly queries our brain to get our judgment, and we may not even need to know that we were queried

Glen avatar
Glen@try_glen·Oct 30

You can now use Glen with Claude Code cloud agents!

Nikos@nikos1Oct 30

After a looooong wait, you can now use Glen in Claude Code Cloud. It's super easy to set up, and you can have Glen working with your cloud agent in just a few minutes. It's possibly one of the easiest, lowest-lift things that you can add to your dev tool stack to dramatically increase your shipping speed.

0:46
Nikos avatar
⟳ Glen retweeted
Nikos@nikos1·Oct 29

Glen is now available on @composio. Glen makes your agents smarter as work happens accross your company.

0:10
Composio avatar
⟳ Glen retweeted
Composio@composio·Oct 29

Now you can combine the power of taking action with Composio and powerful agent memory with Glen!

Nikos@nikos1Oct 29

Glen is now available on @composio. Glen makes your agents smarter as work happens accross your company.

0:10
Tri avatar
⟳ Glen retweeted
Tri@TridhatriV·Oct 28

Glen is just amazing ! try it out !

Nikos@nikos1Oct 28

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.

1:27
Glen avatar
Glen@try_glen·Oct 28

Glen is now open to the public!

Nikos@nikos1Oct 28

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.

1:27
Glen avatar
Glen@try_glen·Aug 20

Check the comments on how to apply for access

Nikos@nikos1Aug 20

Glen is building the organizational learning and context layer for agents. Every agent session your team runs produces reasoning worth keeping, and nearly all of it is discarded the moment the window closes. Glen is the layer that unifies every agent and model your company run. Glen pulls in agent sessions from Claude Code, Codex and Cursor, plus Slack messages, GitHub prs, tickets, docs and calls. When a new agent picks up a task, Glen finds relevant prior context and injects it in the agents context window to steer it, producing knowledge work that is significantly higher quality, faster and cheaper than ever before. 29% less context and 21% faster to be exact. And Glen does more... > query the original agent behind any line of code > search every session your org has ever run > dynamic skill distillation > multiplayer agents > unified transcripts you can hand between Claude Code, Codex, and Cursor mid-task, > a company brain in Slack. Glen is in early access, sign up for the waitlist below.

2:29