Hey everyone! I'm Nikos, the founder of Glen.

TL;DR

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.

https://drive.google.com/file/d/1T0CkjYfo3k3FB40_R7UPNfONO-SdgfKB

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.

And Glen does more. It unifies all of your org's context: 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, and a company brain in Slack.

Composio scaled usage from 2 users to org wide. Over a dozen SF startups use Glen. I’m onboarding new teams every week, email me at nikos@tryglen.com to get set up with early access.

What Glen does practically

• Relevant context injected on every prompt which steers your model to do knowledge work more efficiently saving your time, money and headaches. These injections can consist or niche knowledge unique to the repo you are working in, high level understanding of relevant sub systems, and previous approaches teammates took to similar problems. Glen surfaces the prior work that matters automatically, so tasks finish faster and cost fewer tokens with no loss in quality, because what lands in the window is the relevant work rather than more of it. You can lazy-prompt instead of retyping the same background every session. So far, internal evals show about a 29% reduction in token spend and 21% reduction in task completion time.

  
  Also…

• PR review with the original context. Highlight any code in a diff and ask why it's there. Glen queries the agent session that produced it and answers from the actual trace instead of guessing from the diff.

• Code search across every agent trace. Ask your coding agent anything about the codebase and it searches every session any agent in your org has run, so the answer comes from the work that produced the code.

• A skill library the whole org shares. Glen distills what your team does into skills, publishes them where everyone can use them, and surfaces the right one automatically when someone hits a task it covers.

• Multiplayer agents. You and your designer work the same deck in parallel, you on copy and them on design. Make a design edit and your agent applies the style theirs has learned. When they touch the copy, their agent writes in the voice yours was taught. Neither of you hands anything off.

• No lock-in to a model provider. Transcripts from Claude Code, Codex, and Cursor all land in one place, and you can hand a session from one to another mid-task, with Glen converting the format so the next agent picks up exactly where the last one stopped. Your context, your skills, and your shared artifacts come with you, so moving between providers costs nothing.

• We have a Slackbot company brain too!

Deployed org-wide at Composio. Composio was my first design partner. It started with two users, grew to about twenty naturally as I iterated on the product, and is now used across the company. Also in use at over a dozen other companies!

In the last 30 days alone, Glen injected 10s of millions of characters of organizational context into their agents. These injections steer the models used by these teams, giving them a competative edge that allows them to perform knowledge work better, faster, and cheaper.

My Ask

If you are at a startup and are reading this, there's a 80% chance Glen would be a great addition to your productivity stack. Most teams run agents heavily, and if yours is tired of re-explaining meetings, Slack, tickets, conventions, and what past sessions already worked out, that's exactly what Glen removes.

I'd love to chat, and I'll come to your office, or wherever you are, and set you up for a with a early access workspace before public availability. Just shoot me an email at nikos@tryglen.com!