Dosu @dosu.dev · 13hHow much better would a coding agent actually perform if it had the right memories from the start? VibeMemBench tries to answer that before testing existing memory systems. Devin explains why that made the benchmark the best memory one so far. 100
Dosu @dosu.dev · 30/09/2026Most AI memory benchmarks do not test for what real coding agents actually need to be good at: learning across long histories of work. But our team thinks VibeMemBench does and it is why it sits alone in S-Tier for Michael👇️ 100
Dosu @dosu.dev · 29/09/2026Your agent runs pytest again. In the last session, it learned that make test-int starts the database the tests need. That lesson may still be saved, but never retrieved. Before correcting your agent again, check what made it into context. go.dosu.dev/episodic-mem... 020
Dosu @dosu.dev · 29/09/2026Knowing something and knowing how to do something are very different kinds of memory. EvoMemBench tries to measure both. Devin breaks down why that makes it interesting for real-world agents and where it still falls short for coding. 101
Dosu @dosu.dev · 28/09/2026What if AI memory systems look bad because we’re measuring the wrong thing? Task completion alone doesn’t tell us much anymore. Did the agent learn from past work? Repeat old mistakes? Need the same human correction again? Michael thinks our benchmarks need to change. 210
Dosu @dosu.dev · 23/09/2026It's Dosu Drop Day! 🎒 For our back-to-school edition, Dosu does the studying. When a coding session ends, Dosu writes down what your team would otherwise rediscover. 📝 Session-end study 🧾 Knowledge read cards 💳 Credits that go further go.dosu.dev/drop-sep26-bsky 053
Dosu @dosu.dev · 23/09/2026The team keeps working after the agent’s session ends. @devstein.bsky.social on how merged PRs and resolved conversations keep agent memory current. Recording + transcript: dosu.dev/webinars/age... 022
Dosu @dosu.dev · 22/09/2026Who reviews agent memory when people can’t keep up? Michael Mangus, Head of Product at Dosu, on trusting AI to maintain memory—and making mistakes easy to correct. Recording + transcript: dosu.dev/webinars/age... 011
Dosu @dosu.dev · 21/09/2026A summary of a summary keeps getting further from the source. Michael Mangus, Head of Product at Dosu, explains how repeated summaries lose details in agent memory. Recording + transcript: dosu.dev/webinars/age... 022
Dosu @dosu.dev · 18/09/2026Wrong memory can be worse than no memory. @devstein.bsky.social explains why stale agent memory can undo the value of remembering anything at all. dosu.dev/webinars/age... 033
Dosu @dosu.dev · 19/08/2026It's Dosu Drop Day! 🗄️ Your Claude Code, Codex, and Cursor logs hold answers you keep spending tokens on. Now, Dosu stores them. 1. Backfill your Library from agent logs 2. Configure Dosu by asking Dosu 3. Analytics on login 4. See what knowledge your agent used go.dosu.dev/drop-aug26-b... 011
Dosu @dosu.dev · 18/03/2026Also in this drop -> Doc Reviews get quite the upgrade. Edit proposed changes in place, see change summaries at a glance, and better quality updates across the board. Plus a new blog post on catching documentation drift with Claude Code and GitHub Actions. 110
Dosu @dosu.dev · 06/03/2026One unspoken agreement among every engineering team is that someone will update the docs... later. So, we built a GitHub Actions workflow that catches doc drift on merge, and wrote down every sharp edge we hit. dosu.dev/blog/how-to-... 031
Dosu @dosu.dev · 25/02/2026Also in this drop. MCP Server is available to everyone, one click for Cursor, one command for Claude. Plus a new case study where Bluefin went from 42-hour support response to 12 minutes across 139 repos! 000
Dosu @dosu.dev · 17/12/2025It's Dosu Drop Day! ❄️ This month, we have doc review diffs, image uploads, style guidelines, shareable links, and a CNCF case study to share! dosu.dev/blog/december-2025-dosu-drop 041
Dosu @dosu.dev · 28/07/2025Join @devinstein.bsky.social for July's AMA about Public Spaces, July Dosu Drop and anything else you wanna ask. Link to the event in reply 👇 110
Dosu @dosu.dev · 01/07/2025Honored to be featured in @github.com's first "Awesome Continous AI" list. Read all about it! 👇 go.dosu.dev/74utNAE 022