All activity
kxbnbleft a comment
Hey! I built toran because I got tired of the same debugging loop: something's broken, I can't see what my code is actually sending to the API, and now I'm either adding print statements everywhere or fighting with proxy tools that need cert setup. toran is stupid simple. You swap your base URL and watch requests show up in your browser. That's the whole thing. No SDK to install, no config...
toranDebug any API with a URL swap. No SDK needed.
toran lets you inspect outbound API calls with a simple URL swap. No SDK, no proxy setup, no code changes.
Swap your base URL → watch requests stream live in your browser.
See method, path, headers, status codes, timing and full request/response bodies.
Built for AI/MCP developers debugging agent tool calls, backend engineers working with third-party APIs and anyone tired of console.log debugging.
Read-only by design. Sensitive headers redacted. Single-digit ms overhead. No sign-up required.
toranDebug any API with a URL swap. No SDK needed.
kxbnbleft a comment
Share Chat is what caught my eye. Saw Aleksandr's question about context drift and the chronological serialization answer makes sense for keeping things consistent. But I'm wondering about the opposite case - in pair programming you sometimes want to explore two competing approaches before picking one. With a single shared timeline, would you need separate chat sessions for each idea and merge...
Dropstone 3The first multiplayer AI code editor. Now with Share Chat.
kxbnbleft a comment
The self-healing angle is what caught my eye. We've had the same problem on the API side -- test suites that break every time a response schema changes slightly. Plain language intent over rigid assertions makes a lot more sense for mobile where the UI shifts constantly. How deep does the backend validation go? Can it check things like response status codes and payload structure, or is it...
QuashA mobile QA agent that runs tests without scripts
kxbnbleft a comment
I maintain about 15 Claude Code skills for my daily workflow and the portability problem is real. Right now if I want the same behavior in Cursor I'm manually rewriting CLAUDE.md into .cursorrules. The translate command would save me a lot of time. Curious about the memory feature -- how does it handle conflicting patterns across projects? Like if I have one repo that uses snake_case and...
SkillkitThe package manager for AI agent skills
kxbnbleft a comment
Been using Ghostty as my daily driver for a while now and even contributing to the repo. Cool to see someone building an SSH client on top of it. The iCloud sync for connections is a nice touch -- switching between Mac and iPad is where I always lose my SSH configs. How does it handle key management? Do private keys stay in Keychain or do they sync too?
VVTermGhostty-powered SSH client for iOS, iPad, MacOS.
kxbnbleft a comment
Hey everyone, I built Axiomo because AI code review tools kept solving the wrong problem for me. They all want to be a second developer on your PR. Catching lint issues, suggesting refactors, rewriting your code. That stuff is fine but it's not what makes PR review hard. What makes it hard is context. Who wrote this? Have they touched this area before? What are they actually trying to do?...
AxiomoPR intent and context signals, not AI code review noise
kxbnbleft a comment
Board context → code is the direction I keep thinking about. But it raises a question I don't have a good answer for: once an agent can read your PRD board, who decides if it can also edit it? Or read board A but not board B? MCP is great for connectivity. The permissions side feels underspecified though. We're working on this problem at keypost.ai - basically a policy layer for MCP servers....
Miro MCPTurn code into visual docs, board context into code
kxbnbleft a comment
This hits a real gap. Most debugging tools show you what the code thinks it did, not what actually showed up. We built toran.sh around the same insight for APIs — logs say one thing, the wire shows another. Screen capture is that idea applied one layer up. How do you handle the privacy side? Screens inevitably show stuff that shouldn't get indexed.
screenpipeYour AI finally knows what you're doing
kxbnbleft a comment
Worktrees for agent isolation is the right primitive here. Way cleaner than the branch-switching mess most setups end up with. The part I'm most curious about is the automations running on schedules. Once agents are doing things in the background on a timer, how do you decide what they're allowed to do? That's the part that always gets hand-wavy — everyone focuses on capability but the...
Codex by OpenAIA command center for working with agents
kxbnbleft a comment
The chunk-based indexing over full-page is a good decision — we've seen the same thing where full-page retrieval just drowns the context window with noise. One thing I keep running into with MCP servers like this: once you're exposing content as tools, you eventually need to control who can call what. We're building keypost.ai for exactly that — policy enforcement at the MCP layer. Might be...
YavyTurn any website into an MCP server for AI
kxbnbleft a comment
Native RAG with agentic capabilities in any Mac app is a compelling combo. Curious about the boundary between what the agent can access vs what stays local - do you have explicit permission controls for when it reads from different apps? That's often where trust breaks down in desktop AI assistants.
FluentAgentic AI in Any Mac App. Now with Native RAG
kxbnbleft a comment
Open source billing infrastructure is crucial for SaaS builders who want transparency into their revenue ops. Really appreciate that this is on GitHub - being able to fork and customize pricing logic is a real advantage over closed billing platforms. What's the migration path like for teams already on Stripe Billing?
MeteroidBilling platform to launch, test, + scale business models
kxbnbstarted a discussion
Building a zero-setup API debugger, would love feedback
Hey PH I'm working on toran, a live API inspection tool that works with just a URL swap. No SDK, no proxy config, no cert setup. The problem - I couldn't see what my code was actually sending to third-party APIs. Debugging meant console.logs everywhere or messing with Charles/Proxyman certs. toran is simple. You swap your base URL (like api.openai.com becomes ns262aajok1jv.toran.sh) and watch...
kxbnbleft a comment
The context-aware AI reading the terminal buffer is the killer feature here. Copying error logs into a browser tab to debug has always felt broken. Curious about the BYOK setup - when switching between providers (say OpenAI for one task, DeepSeek for another), does it remember which model works best for different types of errors? Or is it manual switching each time?
APX TerminalEncrypted terminal and SSH client with built‑in AI assistant
kxbnbleft a comment
Nice focus on the local development workflow - the "no more ngrok or ChatGPT subscription needed" angle is a real pain point. The tool inspector for resources, prompts, and OAuth flows looks especially useful. Debugging OAuth in MCP integrations has been frustrating in my experience. One question: does the LLM playground support streaming responses, or is it request/response only? We've found...
MCPJam InspectorTest + develop ChatGPT apps and MCP apps (ext-apps) locally
kxbnbleft a comment
The focus on location APIs specifically is smart - those are notoriously hard to debug when things go wrong (coordinates that look valid but aren't, geocoding edge cases, etc.). Curious how you handle visualizing failed requests vs successful ones? We've found that seeing the actual request/response payloads is often more useful than just status codes when debugging API issues. Congrats on the...
QuetzlyTest, monitor, and visualize your location APIs in one place
kxbnbleft a comment
Love the focus on automation over just visibility. Cost observability is only useful if you can enforce policies and take action automatically. The AI agent approach for explaining anomalies and assigning tasks is clever - moves beyond dashboards into actionable workflow. How do you handle policy enforcement for cost limits and guardrails across different teams? Curious about the governance layer.
CloudchiprCloud costs observability,management and automation platform