Entire Checkpoints
Shares rank 4 of 5 session sharing tools by recommenders
Recommended for keeping AI agent session transcripts linked to commits, to see why code was written. Critics say git already does this and the context could be costly.
Recommended for keeping AI agent session transcripts linked to commits, to see why code was written. Critics say git already does this and the context could be costly.
17 people gave an opinion
- recommend it
- 6
- criticize it
- 11
- approval share
- 35%
Recommended in 2 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 6 people recommend itNeeds 10 or more, not met.
- 0.5 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 2 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Traces why agent code was written
“Checkpoints capture the full session alongside the commit: the transcript, prompts, files touched, token usage, tool calls and more.”
Comment from 10 Feb 2026 in “Ex-GitHub CEO Launches a New Developer Platform for AI Agents” “it'd be great for my agentic workflows where I need to figure out why something was done a specific way”
Comment from 11 Feb 2026 in “Ex-GitHub CEO Launches a New Developer Platform for AI Agents” Found useful in practice
“I copied it for my own tooling to make it work a bit better for my workflows.”
Comment from 2 Mar 2026 in “If AI writes code, should the session be part of the commit?” “I've found immense value in this”
Comment from 11 Feb 2026 in “Ex-GitHub CEO Launches a New Developer Platform for AI Agents” “I find such things to be useful.”
Comment from 11 Feb 2026 in “Ex-GitHub CEO Launches a New Developer Platform for AI Agents”
What people warn about
Each mark is one comment
Git already does this
“Yes we don't see value in taking a git primitive like "commit" and renaming it to "checkpoint"”
Comment from 11 Feb 2026 in “Ex-GitHub CEO Launches a New Developer Platform for AI Agents” “You don't need a dedicated tool to store agent session transcripts and link them to commits.”
Comment from 11 Feb 2026 in “Ex-GitHub CEO Launches a New Developer Platform for AI Agents” “Git already “checkpoints” your code and they can’t time travel your LLM conversation.”
Comment from 11 Feb 2026 in “Ex-GitHub CEO Launches a New Developer Platform for AI Agents” Context could burn many tokens
“after a thousand turns, won't it make just doing a "git checkout" start to be really heavy?”
Comment from 11 Feb 2026 in “Ex-GitHub CEO Launches a New Developer Platform for AI Agents” “wouldn't trying to pull N checkpoints into context of the N+1 task be MUCH more expensive?”
Comment from 11 Feb 2026 in “Ex-GitHub CEO Launches a New Developer Platform for AI Agents” “Sounds way more noisy than anything, and a great way to burn through tokens.”
Comment from 11 Feb 2026 in “Ex-GitHub CEO Launches a New Developer Platform for AI Agents” Seen as trivial or overhyped
“a fucking text file that contains the conversation you've had with the bot so-far”
Comment from 11 Feb 2026 in “Ex-GitHub CEO Launches a New Developer Platform for AI Agents” “It's just very fancy marketing speak for the exact same thing.”
Comment from 11 Feb 2026 in “Ex-GitHub CEO Launches a New Developer Platform for AI Agents” “i mean all that is trivial. not worth a $60MM investment.”
Comment from 11 Feb 2026 in “Ex-GitHub CEO Launches a New Developer Platform for AI Agents” - Comment from 11 Feb 2026 in “Ex-GitHub CEO Launches a New Developer Platform for AI Agents”
Other session sharing tools people recommend
The four most recommended other session sharing tools, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Claude-replay | 13 | 0 | 100% | 1 | — | — |
| Claudebin | 12 | 0 | 100% | 2 | — | — |
| Traces | 11 | 0 | 100% | 4 | — | Approved |
| Entire CheckpointsThis page | 6 | 11 | 35% | 2 | — | — |
| Supafork | 6 | 0 | 100% | 1 | — | — |
What people said
All 17 comments that mention it, newest first. Each links to the original comment.
“I copied it for my own tooling to make it work a bit better for my workflows.”
“I find such things to be useful.”
“You don't need a dedicated tool to store agent session transcripts and link them to commits.”
“Yes we don't see value in taking a git primitive like "commit" and renaming it to "checkpoint"”
“I've found immense value in this”
“a fucking text file that contains the conversation you've had with the bot so-far”
“it'd be great for my agentic workflows where I need to figure out why something was done a specific way”
“Dump a bunch of JSON from llm proxy and commit it ?”
“they will need to iterate fast for this not to be made obsolete before they can even release something”
“i mean all that is trivial. not worth a $60MM investment.”
“Git already “checkpoints” your code and they can’t time travel your LLM conversation.”
“I find the framing of the problem to be very accurate, which is very encouraging.”
“wouldn't trying to pull N checkpoints into context of the N+1 task be MUCH more expensive?”
“Sounds way more noisy than anything, and a great way to burn through tokens.”
“It's just very fancy marketing speak for the exact same thing.”
“after a thousand turns, won't it make just doing a "git checkout" start to be really heavy?”
“Checkpoints capture the full session alongside the commit: the transcript, prompts, files touched, token usage, tool calls and more.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.