ctx
Hacker ApprovedShares rank 8 of 26 agent orchestrators by recommenders
People recommend ctx for searching and resuming coding agent history across Claude Code and Codex, and its token efficiency. The most common caveat is a paywall.
People recommend ctx for searching and resuming coding agent history across Claude Code and Codex, and its token efficiency. The most common caveat is a paywall.
18 people gave an opinion
- recommend it
- 13
- criticize it
- 5
- approval share
- 72%
Recommended in 6 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 13 people recommend itNeeds 10 or more, met.
- 2.6 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 6 of 13 monthsNeeds 4 or more, 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
Search over agent conversation history
“Obviously, your tool does not provide this. But I think GP is undervaluing the UX advantages of having your conversation history.”
Comment from 21 Apr 2026 in “Show HN: Ctx – a /resume that works across Claude Code and Codex” “semantic search has been pretty good, it usually finds what it's looking for”
Comment from 3 Jul 2026 in “Show HN: ctx – Search the coding agent history already on your machine” “I use https://usegitai.com/ and https://ctx.rs/ to preserve and search them.”
Comment from 15 Jul 2026 in “Show HN: Grepathy – Claude made a decision nobody approved” - Comment from 3 Jul 2026 in “Show HN: ctx – Search the coding agent history already on your machine”
Token efficiency and accurate results
“What really ended up being the big efficiency improvement is the token efficiency.”
Comment from 3 Jul 2026 in “Show HN: ctx – Search the coding agent history already on your machine” “ctx results are more accurate, ergonomic, and token efficient”
Comment from 3 Jul 2026 in “Show HN: ctx – Search the coding agent history already on your machine” Isolated VM and container runs
“ctx can run work in VM/container-isolated environments with explicit network policy”
Comment from 3 Apr 2026 in “Show HN: ctx – an Agentic Development Environment (ADE)” “we automatically manage a lot of the VM complexity including elastic memory”
Comment from 3 Apr 2026 in “Show HN: ctx – an Agentic Development Environment (ADE)” Local-first, well considered design
“thanks for making it local-first!”
Comment from 21 Apr 2026 in “Show HN: Ctx – a /resume that works across Claude Code and Codex” “it feels deeply considered”
Comment from 3 Apr 2026 in “Show HN: ctx – an Agentic Development Environment (ADE)”
Other agent orchestrators people recommend
The four most recommended other agent orchestrators, 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 |
|---|---|---|---|---|---|---|
| Gas Town | 95 | 212 | 31% | 10 | 1 mo3 owners | — |
| Conductor | 58 | 25 | 70% | 11 | — | Approved |
| Superset | 33 | 16 | 67% | 8 | 2 mo4 owners | Approved |
| Scion by Google | 28 | 32 | 47% | 8 | — | — |
| ctxThis page | 13 | 5 | 72% | 6 | — | Approved |
What people said
27 of the 29 comments that mention it, newest first. Each links to the original comment.
“I struggle with the paywall though”
“The performance changes are really significant”
“It deterministically pulls the full session log so you don't need to tell an LLM to do it”
“I use https://usegitai.com/ and https://ctx.rs/ to preserve and search them.”
“When it comes to coding sessions my problems are memory and inter-agent communication, for which I'm using”
“stop emailing people from the AUR using your stupid email handle to advertise your ai slop”
“ctx results are more accurate, ergonomic, and token efficient”
“Really nice idea - there is certainly gold in the history of agent actions.”
“I like the CLI interface, very comprehensive.”
“semantic search has been pretty good, it usually finds what it's looking for”
“OP's tool is cool, and worth trying.”
“Great project btw. Interesting choice to trigger incremental refresh on SessionStart hook, that's nice.”
“What really ended up being the big efficiency improvement is the token efficiency.”
“We realized we wanted our ADE to work like that too.”
“There are some interesting concepts in the repo if you dig in”
“There are quite a few interesting technical details in the repo”
“this switch is going to burn subscription limits on Claude real real fast”
“thanks for making it local-first!”
“Obviously, your tool does not provide this. But I think GP is undervaluing the UX advantages of having your conversation history.”
“we automatically manage a lot of the VM complexity including elastic memory”
“it feels deeply considered”
“There's no code, no license, no nothing.”
“agent-driven conflict resolution via a merge queue works really well in practice”
“That's a bummer, especially since folks normally use the .rs TLD for Rust projects”
“window is blank on launch, and menu bar is all greyed out”
“ctx can run work in VM/container-isolated environments with explicit network policy”
“Really cool, would love to have window management as a part of this.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.