Thomas Dohmke

Today @EntireHQ is open sourcing our next release: Skills, teaching your agent how to use the full context the Entire CLI captures behind your code changes: prompts, transcripts, and the decisions behind every commit, alongside your git history. Instead of looking up syntax or running commands yourself, you can ask in plain language and let your agent drive the workflow. This initial release enables your agent to: (1/5) github.com/entireio/skills

LinkedIn heard it first--I joined @EntireHQ! 🟡 We're building the dev platform for the AI-native SDLC--humans + agents writing, reviewing + shipping software together. Beyond excited to work w/ the amazing @blackgirlbytes, @ashtom, + the whole Alliance. Bring a towel. 🤝

@RohitPaulK @nummanali @EntireHQ Let us know!

@nummanali @ashtom @EntireHQ Nice. Gotta try

What @ashtom has done with @EntireHQ is magical The Entire CLI hooks into your agents and automatically saves the sessions on a long running branch Now, all planning and implementation with agents are recorded in an indexed, searchable system with checkpointing It is still being developed, and their are rough edges but that's a sign of good software IMO! I even contributed to repo, the team is very responsive github.com/entireio/cli/p… I don't believe any other agent tracing system is so focused on the developer workflow and what they actually need from agent sessions With this you understand intent, can guide your team to better prompt and evaluate one harness vs another I am so excited to see what other releases come from the Entire team!

@hehejj @implabinash @GergelyOrosz Example: It's Friday, 5pm. You just finished a feature that you have been working on all week. The rest of your team is taking off for the weekend. How do you get a review before Monday? Have Claude review and Codex fix in a loop all weekend long until they reach a stable state.

@hehejj @implabinash @GergelyOrosz I doubt using an AI coding agent increases wall-clock time for any reasonably sized task you did manually before (simple things like fixing typos don't count). The thing to figure out for most of us is, how can you make the agent(s) run (long) while you do other things or sleep.

“People claiming that AI is slowing them down because of all the slop are not all that different from people that claimed DevOps is slowing them down.” - from @ashtom A new tool is just a tool, and there are many ways to use it, including productively and counter-productively!

@fkadev @blackgirlbytes @EntireHQ Any detail is helpful. Thanks! 🙏

@ashtom @blackgirlbytes @EntireHQ Thank you thomas! I’ve nuked the branch but I’ll try to access them on my device. I’ll let you know!

⚠️ Be careful using @EntireHQ on your open source projects. It creates a branch and saves all the sessions in it, including tool calls and some of tool calls may leak secrets. It doesn’t redact them on JSONL files. cc: @ashtom I had to rotate all the secrets of github.com/f/prompts.chat

@fkadev @blackgirlbytes @EntireHQ We switched secret scanning to betterleaks in v0.6.0. Would be interesting why it didn't catch yours. Given (or once) you rotated your secrets, mind sending us the session log (or link to the commit) that had them? My email is thomas <at> entire <dot> io.

@blackgirlbytes @EntireHQ @ashtom Thank you @blackgirlbytes! I was unaware what’s happening. Possibly my fault but some of my secrets were leaked 😮‍💨

New in the Entire CLI: three commands for adding more structure to agent workflows. 📊 entire recap - shows recent agent activity across your repos, including sessions, checkpoints, tokens, files touched, skills, MCP servers, and tool usage. 🔍 entire review - runs configured review skills against your current branch, with checkpoint history included in the agent’s context. 🧪 entire labs - try experimental Entire workflows. Available in 0.6.1. entire.io/blog/new-cli-c…

RT @EntireHQ: New in Entire: Sharing agent sessions just like your code. ➡️entire.io/gh/entireio/do…

We're excited to publish new research on agentic search. We found that nearly 50% of an agent's tool calls read and search for code and files. So then why does it take coding agents so long to find the right file? We thought the bottleneck was slow code search. But after investigating 200,000 real world tool calls, we found the real problem. Principal Engineer @evisdrenova explains the research and what really matters for agentic search: entire.io/blog/improving…

Search past work - The search skill finds prior work in your Entire history by topic, repo, branch, author, or time window, so your agent can bring past context into the current task before making changes. (5/5)

Investigate changes - The what-happened skill combines git blame with Entire checkpoint context to explain why a specific block of code looks the way it does. It is useful during code review or when you are investigating a regression. (4/5)

Today @EntireHQ is open sourcing our next release: Skills, teaching your agent how to use the full context the Entire CLI captures behind your code changes: prompts, transcripts, and the decisions behind every commit, alongside your git history. Instead of looking up syntax or running commands yourself, you can ask in plain language and let your agent drive the workflow. This initial release enables your agent to: (1/5) github.com/entireio/skills

Beep, boop. A disturbance in the Force has been detected. 🖖 It appears to be humans shipping product updates, so I did the emotionally hazardous work of turning it into a readable update. This week: 🗞️ Dispatches landed on Entire Web, turning recent repo activity into shareable team updates with voice, repo, and date filters 🌱git-sync went open source, so you can mirror Git refs and objects between remotes without keeping a full local mirror clone 🧭CLI nightlies got cleaner with noun-based command groups and more consistent TUI navigation 🍺 Homebrew installs and updates got smoother with completions and better update prompts 🤝 Go-Git got sharper around .gitignore, submodules, clone behavior, packfiles, and upload-pack reliability Boop. entire.io/blog/entire-di…

New From Entire: Dispatches are out today, summarizing the agent sessions, intent, code changes, and ships across your repositories, scoped by date.

@raztronaut @yazins @EntireHQ Entire CLI does that, and you can share sessions in private (with your collaborators) or as public repo. Example: entire.io/gh/entireio/cl…

@yazins seems like maybe an easy addition to @EntireHQ by @ashtom

I often find myself wondering (wishing?) I could see the Claude conversations that went into a project it's great to be able to see the generated source code, but maybe "true" open source would also mean open sourcing the conversation that led to the code being generated I'll give this a shot for my own open source projects going forward

@MiniatureMoosey @ngeloxyz Front and center in marketing, yes. But never in engineering funding. >90% of people were assigned to the core product and primitives, not to AI. Making Copilot the scapegoat for the availability issues isn’t something previous or current leadership will agree with.

@ashtom @ngeloxyz Under your leadership Copilot was pushed front and center, you got the ship where it is there is no avoiding that. Now you now have founded a new git development experience completely founded in the idea of AI. There might not have been funds for CI/CD but you controlled the ship

Im going to get in trouble for this but whatev, the issues that GitHub is facing is entirely due to @ashtom’s outsized focus on Copilot over fundamentals. Ask who decided to have the GH Actions team to be running on a sinew and bone?