Show HN: ctx – an Agentic Development Environment (ADE)
luca-ctx
OP here. Happy to answer questions.
The multi-thread, worktree-based interface will probably look familiar. The parts HN may care more about are the containerized workspaces, remote-host model, and local merge queue for multi-agent work.
xrd
I'm honestly having trouble understanding all the benefits and drawbacks of the different agents, specifically around what I want to permit for permissions.
My solution has been to create a new VM which inherits a Claude cli and Gemini CLI pre installed.
That way I can configure at a host level all the permissions I want and it is less likely the agent will access full sets of files and even worse delete things. I know this limits what I can do, but I am exhausted my understanding and auditing the different options for each agent.
I can install a new agent on that VM and then try it, but it is hard to justify the effort to test each one.
What am I getting from your tool for example? Worktree support is somewhat common, right? Does this give me multi agent support that Gemini and Claude do not, does that mean collaboration across team members? Is your approach better, or safer, than what I'm doing? How do I verify those claims?
Can I use your tool with local models like gemma 4 and ollama/llama.cpp: I have 3 24gb Nvidia cards and would like to try a three agent approach, one to write the code, one to write tests, one to architect. I obviously can't use local models with Gemini and Claude cli.
I'm just riffing on my concerns, and thanks for listening.
unsubtlecoder
Interesting, one challenge with other ADEs (nice term btw) like Conductor is that code navigation is terrible and too much emphasis is on a GUI for Claude.
We really need the best of both worlds: IDE (powerful like Intellij) + ADE (multitasking code)
And how does it compare to other tools like Conductor?
luca-ctx
Yes, our view is that the ADE shouldn’t be where you do most code navigation.
The ADE is best for steering multiple agents and reviewing their changes, especially once you care about isolated worktrees, diffs, artifacts, and landing changes cleanly.
When you need deep code navigation, the best answer is usually to open the worktree in your IDE. IDEs are already world-class at navigation and refactoring, so there’s no reason to rebuild that badly inside an agent UI.
Compared with Conductor, a few differences:
- Conductor relies mostly on the safety model of the underlying harnesses; ctx can run work in VM/container-isolated environments with explicit network policy.
- ctx has a local merge queue for landing changes from multiple agent worktrees onto each other.
- Conductor is a local Mac app; ctx also works with Linux and is designed for the “local app + remote Linux runtime” model for devapp/VPS.
- Conductor is focused mainly on Claude Code and Codex; ctx is meant to be a broader environment around multiple harnesses.
There are also substantial UX differences, but those are easier to judge by trying them.
Bnjoroge
Agree with this. I find myself switching panes between conductor or codex and zed because of code navigation. Maybe that's what cursor is trying to do in their new version, but I havent tried it yet
mattv8
Very nice. Does this support GitHub Copilot subscriptions (oauth/hmac) or do you have plans for it? That would make or break for me because of the API costs.
Similarly I built a self-host able replit-like server with RAG but it's more end-user focused than developer focused...
luca-ctx
Yes. The important distinction is that ctx sits above the agent harness, not above the raw model APIs.
With something like Cursor, you can use models from OpenAI, Anthropic, etc, but they still run through Cursor’s own agent harness.
With ctx, you bring the existing harness itself — Copilot, Claude Code, Codex, and so on — and it keeps its own auth/billing/session model. ctx is the layer around that: worktrees, review, runtime boundaries, merge queue, etc.
Remi_Etien
[dead]
aiiaro
[dead]
leetvibecoder
Does this solve indexing of codebases like Cursor does, or do you still need tools / plugins like Lumen (https://github.com/ory/lumen) for that in order to work in larger codebases without wasting tens of thousands of tokens on tool calls and brute force guessing with grep?
ctx sits around the agent harness, not in place of it.
So Claude Code, Codex, OpenCode, etc keep their normal tools/capabilities rather than being reimplemented inside a new proprietary agent. If a harness has its own indexing/code-search story, you still get that; if it doesn’t, ctx doesn’t provide additional tools like codebase indexing.
The only additional tools we do provide are orchestration-related:
- local merge queue for agents (submit your diff and make sure it lands cleanly on others)
- agnostic subagents (for example, a Claude Code primary agent can invoke a Codex subagent)
bloppe
I don't understand why so many people building agents feel the need to fork and maintain a whole IDE as well
Bnjoroge
because you probably need both if you are doing guided agentic work. IDE gives you the familiar benefits, especially code nav. If you are using background agents or launching agents without reviewing their work, then I guess you dont need an IDE.
luca-ctx
I agree. I don’t think most of these products should be forking and maintaining a whole IDE.
That’s also not how I think about ctx. The UI is a workbench around agents, not a replacement for IntelliJ/VS Code. If you need deep code navigation, refactors, debugger-heavy work, etc., the right answer is usually to open the same worktree in your IDE.
ctx includes surfaces for diff review and an integrated terminal, but not code editing or a full-fledged IDE. It's not a fork of VSCode.
throwif
exactly tmux + claude code + your real editor. the ide tax is real and nobody benchmarks it
Bnjoroge
Looks cool! Two things: I see you mentioned the merge queue, but how exactly do people avoid or resolve merge conflicts when merging work from two or more agents in the separate worktrees? I havent really seen a seamless way to approach this or do people just have the agents work on distinctly unrelated stuff? Secondly, are containers the primary sandboxing appraoch? or do you support vms?
nhumrich
Appears to not work on Linux. Just launches, doesn't install an application file, window is blank on launch, and menu bar is all greyed out.
SparkyMcUnicorn
Your repo says it's open source, but it's missing the source.
TLDR: use an ADE if you need multiple agents working concurrently on your code base. Otherwise IDE with an agent plugin is probably fine.
phplovesong
No thanks. We have a strict no-ai policy.
luca-ctx
OP here. Happy to answer questions.
The multi-thread, worktree-based interface will probably look familiar. The parts HN may care more about are the containerized workspaces, remote-host model, and local merge queue for multi-agent work.
xrd
I'm honestly having trouble understanding all the benefits and drawbacks of the different agents, specifically around what I want to permit for permissions.
My solution has been to create a new VM which inherits a Claude cli and Gemini CLI pre installed.
That way I can configure at a host level all the permissions I want and it is less likely the agent will access full sets of files and even worse delete things. I know this limits what I can do, but I am exhausted my understanding and auditing the different options for each agent.
I can install a new agent on that VM and then try it, but it is hard to justify the effort to test each one.
What am I getting from your tool for example? Worktree support is somewhat common, right? Does this give me multi agent support that Gemini and Claude do not, does that mean collaboration across team members? Is your approach better, or safer, than what I'm doing? How do I verify those claims?
Can I use your tool with local models like gemma 4 and ollama/llama.cpp: I have 3 24gb Nvidia cards and would like to try a three agent approach, one to write the code, one to write tests, one to architect. I obviously can't use local models with Gemini and Claude cli.
I'm just riffing on my concerns, and thanks for listening.
unsubtlecoder
Interesting, one challenge with other ADEs (nice term btw) like Conductor is that code navigation is terrible and too much emphasis is on a GUI for Claude.
We really need the best of both worlds: IDE (powerful like Intellij) + ADE (multitasking code)
And how does it compare to other tools like Conductor?
luca-ctx
Yes, our view is that the ADE shouldn’t be where you do most code navigation.
The ADE is best for steering multiple agents and reviewing their changes, especially once you care about isolated worktrees, diffs, artifacts, and landing changes cleanly.
When you need deep code navigation, the best answer is usually to open the worktree in your IDE. IDEs are already world-class at navigation and refactoring, so there’s no reason to rebuild that badly inside an agent UI.
Compared with Conductor, a few differences:
- Conductor relies mostly on the safety model of the underlying harnesses; ctx can run work in VM/container-isolated environments with explicit network policy.
- ctx has a local merge queue for landing changes from multiple agent worktrees onto each other.
- Conductor is a local Mac app; ctx also works with Linux and is designed for the “local app + remote Linux runtime” model for devapp/VPS.
- Conductor is focused mainly on Claude Code and Codex; ctx is meant to be a broader environment around multiple harnesses.
There are also substantial UX differences, but those are easier to judge by trying them.
Bnjoroge
Agree with this. I find myself switching panes between conductor or codex and zed because of code navigation. Maybe that's what cursor is trying to do in their new version, but I havent tried it yet
mattv8
Very nice. Does this support GitHub Copilot subscriptions (oauth/hmac) or do you have plans for it? That would make or break for me because of the API costs.
Similarly I built a self-host able replit-like server with RAG but it's more end-user focused than developer focused...
luca-ctx
Yes. The important distinction is that ctx sits above the agent harness, not above the raw model APIs.
With something like Cursor, you can use models from OpenAI, Anthropic, etc, but they still run through Cursor’s own agent harness.
With ctx, you bring the existing harness itself — Copilot, Claude Code, Codex, and so on — and it keeps its own auth/billing/session model. ctx is the layer around that: worktrees, review, runtime boundaries, merge queue, etc.
Remi_Etien
[dead]
aiiaro
[dead]
leetvibecoder
Does this solve indexing of codebases like Cursor does, or do you still need tools / plugins like Lumen (https://github.com/ory/lumen) for that in order to work in larger codebases without wasting tens of thousands of tokens on tool calls and brute force guessing with grep?
ctx sits around the agent harness, not in place of it.
So Claude Code, Codex, OpenCode, etc keep their normal tools/capabilities rather than being reimplemented inside a new proprietary agent. If a harness has its own indexing/code-search story, you still get that; if it doesn’t, ctx doesn’t provide additional tools like codebase indexing.
The only additional tools we do provide are orchestration-related:
- local merge queue for agents (submit your diff and make sure it lands cleanly on others)
- agnostic subagents (for example, a Claude Code primary agent can invoke a Codex subagent)
bloppe
I don't understand why so many people building agents feel the need to fork and maintain a whole IDE as well
Bnjoroge
because you probably need both if you are doing guided agentic work. IDE gives you the familiar benefits, especially code nav. If you are using background agents or launching agents without reviewing their work, then I guess you dont need an IDE.
luca-ctx
I agree. I don’t think most of these products should be forking and maintaining a whole IDE.
That’s also not how I think about ctx. The UI is a workbench around agents, not a replacement for IntelliJ/VS Code. If you need deep code navigation, refactors, debugger-heavy work, etc., the right answer is usually to open the same worktree in your IDE.
ctx includes surfaces for diff review and an integrated terminal, but not code editing or a full-fledged IDE. It's not a fork of VSCode.
throwif
exactly tmux + claude code + your real editor. the ide tax is real and nobody benchmarks it
Bnjoroge
Looks cool! Two things: I see you mentioned the merge queue, but how exactly do people avoid or resolve merge conflicts when merging work from two or more agents in the separate worktrees? I havent really seen a seamless way to approach this or do people just have the agents work on distinctly unrelated stuff? Secondly, are containers the primary sandboxing appraoch? or do you support vms?
nhumrich
Appears to not work on Linux. Just launches, doesn't install an application file, window is blank on launch, and menu bar is all greyed out.
SparkyMcUnicorn
Your repo says it's open source, but it's missing the source.
OP here. Happy to answer questions.
The multi-thread, worktree-based interface will probably look familiar. The parts HN may care more about are the containerized workspaces, remote-host model, and local merge queue for multi-agent work.
I'm honestly having trouble understanding all the benefits and drawbacks of the different agents, specifically around what I want to permit for permissions.
My solution has been to create a new VM which inherits a Claude cli and Gemini CLI pre installed.
That way I can configure at a host level all the permissions I want and it is less likely the agent will access full sets of files and even worse delete things. I know this limits what I can do, but I am exhausted my understanding and auditing the different options for each agent.
I can install a new agent on that VM and then try it, but it is hard to justify the effort to test each one.
What am I getting from your tool for example? Worktree support is somewhat common, right? Does this give me multi agent support that Gemini and Claude do not, does that mean collaboration across team members? Is your approach better, or safer, than what I'm doing? How do I verify those claims?
Can I use your tool with local models like gemma 4 and ollama/llama.cpp: I have 3 24gb Nvidia cards and would like to try a three agent approach, one to write the code, one to write tests, one to architect. I obviously can't use local models with Gemini and Claude cli.
I'm just riffing on my concerns, and thanks for listening.
Interesting, one challenge with other ADEs (nice term btw) like Conductor is that code navigation is terrible and too much emphasis is on a GUI for Claude.
We really need the best of both worlds: IDE (powerful like Intellij) + ADE (multitasking code)
And how does it compare to other tools like Conductor?
Yes, our view is that the ADE shouldn’t be where you do most code navigation.
The ADE is best for steering multiple agents and reviewing their changes, especially once you care about isolated worktrees, diffs, artifacts, and landing changes cleanly.
When you need deep code navigation, the best answer is usually to open the worktree in your IDE. IDEs are already world-class at navigation and refactoring, so there’s no reason to rebuild that badly inside an agent UI.
Compared with Conductor, a few differences:
- Conductor relies mostly on the safety model of the underlying harnesses; ctx can run work in VM/container-isolated environments with explicit network policy.
- ctx has a local merge queue for landing changes from multiple agent worktrees onto each other.
- Conductor is a local Mac app; ctx also works with Linux and is designed for the “local app + remote Linux runtime” model for devapp/VPS.
- Conductor is focused mainly on Claude Code and Codex; ctx is meant to be a broader environment around multiple harnesses.
There are also substantial UX differences, but those are easier to judge by trying them.
Agree with this. I find myself switching panes between conductor or codex and zed because of code navigation. Maybe that's what cursor is trying to do in their new version, but I havent tried it yet
Very nice. Does this support GitHub Copilot subscriptions (oauth/hmac) or do you have plans for it? That would make or break for me because of the API costs.
Similarly I built a self-host able replit-like server with RAG but it's more end-user focused than developer focused...
Yes. The important distinction is that ctx sits above the agent harness, not above the raw model APIs.
With something like Cursor, you can use models from OpenAI, Anthropic, etc, but they still run through Cursor’s own agent harness.
With ctx, you bring the existing harness itself — Copilot, Claude Code, Codex, and so on — and it keeps its own auth/billing/session model. ctx is the layer around that: worktrees, review, runtime boundaries, merge queue, etc.
[dead]
[dead]
Does this solve indexing of codebases like Cursor does, or do you still need tools / plugins like Lumen (https://github.com/ory/lumen) for that in order to work in larger codebases without wasting tens of thousands of tokens on tool calls and brute force guessing with grep?
how does lumen differ from serena? https://github.com/oraios/serena curious about it seems promising
ctx sits around the agent harness, not in place of it.
So Claude Code, Codex, OpenCode, etc keep their normal tools/capabilities rather than being reimplemented inside a new proprietary agent. If a harness has its own indexing/code-search story, you still get that; if it doesn’t, ctx doesn’t provide additional tools like codebase indexing.
The only additional tools we do provide are orchestration-related: - local merge queue for agents (submit your diff and make sure it lands cleanly on others) - agnostic subagents (for example, a Claude Code primary agent can invoke a Codex subagent)
I don't understand why so many people building agents feel the need to fork and maintain a whole IDE as well
because you probably need both if you are doing guided agentic work. IDE gives you the familiar benefits, especially code nav. If you are using background agents or launching agents without reviewing their work, then I guess you dont need an IDE.
I agree. I don’t think most of these products should be forking and maintaining a whole IDE.
That’s also not how I think about ctx. The UI is a workbench around agents, not a replacement for IntelliJ/VS Code. If you need deep code navigation, refactors, debugger-heavy work, etc., the right answer is usually to open the same worktree in your IDE.
ctx includes surfaces for diff review and an integrated terminal, but not code editing or a full-fledged IDE. It's not a fork of VSCode.
exactly tmux + claude code + your real editor. the ide tax is real and nobody benchmarks it
Looks cool! Two things: I see you mentioned the merge queue, but how exactly do people avoid or resolve merge conflicts when merging work from two or more agents in the separate worktrees? I havent really seen a seamless way to approach this or do people just have the agents work on distinctly unrelated stuff? Secondly, are containers the primary sandboxing appraoch? or do you support vms?
Appears to not work on Linux. Just launches, doesn't install an application file, window is blank on launch, and menu bar is all greyed out.
Your repo says it's open source, but it's missing the source.
https://github.com/ctxrs/ctx
That is our issues-only repo, similar to Claude Code. It is not open source.
I really appreciated this overview of when to use an IDE vs an ADE:
https://ctx.rs/ade-vs-ide
TLDR: use an ADE if you need multiple agents working concurrently on your code base. Otherwise IDE with an agent plugin is probably fine.
No thanks. We have a strict no-ai policy.
OP here. Happy to answer questions.
The multi-thread, worktree-based interface will probably look familiar. The parts HN may care more about are the containerized workspaces, remote-host model, and local merge queue for multi-agent work.
I'm honestly having trouble understanding all the benefits and drawbacks of the different agents, specifically around what I want to permit for permissions.
My solution has been to create a new VM which inherits a Claude cli and Gemini CLI pre installed.
That way I can configure at a host level all the permissions I want and it is less likely the agent will access full sets of files and even worse delete things. I know this limits what I can do, but I am exhausted my understanding and auditing the different options for each agent.
I can install a new agent on that VM and then try it, but it is hard to justify the effort to test each one.
What am I getting from your tool for example? Worktree support is somewhat common, right? Does this give me multi agent support that Gemini and Claude do not, does that mean collaboration across team members? Is your approach better, or safer, than what I'm doing? How do I verify those claims?
Can I use your tool with local models like gemma 4 and ollama/llama.cpp: I have 3 24gb Nvidia cards and would like to try a three agent approach, one to write the code, one to write tests, one to architect. I obviously can't use local models with Gemini and Claude cli.
I'm just riffing on my concerns, and thanks for listening.
Interesting, one challenge with other ADEs (nice term btw) like Conductor is that code navigation is terrible and too much emphasis is on a GUI for Claude.
We really need the best of both worlds: IDE (powerful like Intellij) + ADE (multitasking code)
And how does it compare to other tools like Conductor?
Yes, our view is that the ADE shouldn’t be where you do most code navigation.
The ADE is best for steering multiple agents and reviewing their changes, especially once you care about isolated worktrees, diffs, artifacts, and landing changes cleanly.
When you need deep code navigation, the best answer is usually to open the worktree in your IDE. IDEs are already world-class at navigation and refactoring, so there’s no reason to rebuild that badly inside an agent UI.
Compared with Conductor, a few differences:
- Conductor relies mostly on the safety model of the underlying harnesses; ctx can run work in VM/container-isolated environments with explicit network policy.
- ctx has a local merge queue for landing changes from multiple agent worktrees onto each other.
- Conductor is a local Mac app; ctx also works with Linux and is designed for the “local app + remote Linux runtime” model for devapp/VPS.
- Conductor is focused mainly on Claude Code and Codex; ctx is meant to be a broader environment around multiple harnesses.
There are also substantial UX differences, but those are easier to judge by trying them.
Agree with this. I find myself switching panes between conductor or codex and zed because of code navigation. Maybe that's what cursor is trying to do in their new version, but I havent tried it yet
Very nice. Does this support GitHub Copilot subscriptions (oauth/hmac) or do you have plans for it? That would make or break for me because of the API costs.
Similarly I built a self-host able replit-like server with RAG but it's more end-user focused than developer focused...
Yes. The important distinction is that ctx sits above the agent harness, not above the raw model APIs.
With something like Cursor, you can use models from OpenAI, Anthropic, etc, but they still run through Cursor’s own agent harness.
With ctx, you bring the existing harness itself — Copilot, Claude Code, Codex, and so on — and it keeps its own auth/billing/session model. ctx is the layer around that: worktrees, review, runtime boundaries, merge queue, etc.
[dead]
[dead]
Does this solve indexing of codebases like Cursor does, or do you still need tools / plugins like Lumen (https://github.com/ory/lumen) for that in order to work in larger codebases without wasting tens of thousands of tokens on tool calls and brute force guessing with grep?
how does lumen differ from serena? https://github.com/oraios/serena curious about it seems promising
ctx sits around the agent harness, not in place of it.
So Claude Code, Codex, OpenCode, etc keep their normal tools/capabilities rather than being reimplemented inside a new proprietary agent. If a harness has its own indexing/code-search story, you still get that; if it doesn’t, ctx doesn’t provide additional tools like codebase indexing.
The only additional tools we do provide are orchestration-related: - local merge queue for agents (submit your diff and make sure it lands cleanly on others) - agnostic subagents (for example, a Claude Code primary agent can invoke a Codex subagent)
I don't understand why so many people building agents feel the need to fork and maintain a whole IDE as well
because you probably need both if you are doing guided agentic work. IDE gives you the familiar benefits, especially code nav. If you are using background agents or launching agents without reviewing their work, then I guess you dont need an IDE.
I agree. I don’t think most of these products should be forking and maintaining a whole IDE.
That’s also not how I think about ctx. The UI is a workbench around agents, not a replacement for IntelliJ/VS Code. If you need deep code navigation, refactors, debugger-heavy work, etc., the right answer is usually to open the same worktree in your IDE.
ctx includes surfaces for diff review and an integrated terminal, but not code editing or a full-fledged IDE. It's not a fork of VSCode.
exactly tmux + claude code + your real editor. the ide tax is real and nobody benchmarks it
Looks cool! Two things: I see you mentioned the merge queue, but how exactly do people avoid or resolve merge conflicts when merging work from two or more agents in the separate worktrees? I havent really seen a seamless way to approach this or do people just have the agents work on distinctly unrelated stuff? Secondly, are containers the primary sandboxing appraoch? or do you support vms?
Appears to not work on Linux. Just launches, doesn't install an application file, window is blank on launch, and menu bar is all greyed out.
Your repo says it's open source, but it's missing the source.
https://github.com/ctxrs/ctx
That is our issues-only repo, similar to Claude Code. It is not open source.
I really appreciated this overview of when to use an IDE vs an ADE:
https://ctx.rs/ade-vs-ide
TLDR: use an ADE if you need multiple agents working concurrently on your code base. Otherwise IDE with an agent plugin is probably fine.
No thanks. We have a strict no-ai policy.