I built a smart proxy so your coding agent can run loose
Details
- External ID
- 48907871
- Source
- HN
- Company
- —
- Product
- I built a smart proxy so your coding agent can run loose
- Website domain
- trollbridge.dev
- Launched
- July 14, 2026
- Cohort
- —
- Upvotes
- 14
- Upvotes percentile
- 0.6338112305854241
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
The only way to go fast is full YOLO mode in your coding agent. I've got the local sandbox figured out (pro tip: Incus VMs work great) but I wanted to keep my agents from doing things like inadvertently blowing up my cloud services or chasing a prompt to POST to some random website. I struggle most with this on my side projects where my permission model isn't quite as robust as it is at the office.I started with a firewall on the Incus container but every time the agent needed access to something new, I was poking more holes in it - and it didn't differentiate between HTTP verbs.I've been using Claude Code auto mode too but I wanted to be able to guide the LLM, not just hand over control completely. I also want some flat allow and deny rules.So, I built Trollbridge: an HTTP/S proxy that runs in front of your coding agent and lets you set up allow or deny lists, realtime approve or deny in the TUI, or wire up an LLM that makes calls based on your prior decisions.Would love to hear what you think - give it a shot, leave a comment, file a bug. Thanks!Website: https://trollbridge.dev Github: https://github.com/dandriscoll/trollbridge
Enrichment
- Theme
- AI agent frameworks and developer tools
- Vertical
- Horizontal
- Function
- Agent / copilot
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Hobby / open-source project
- Normalized one-liner
- proxy for running coding agents
- Manually corrected
- False
Could you build this?
Yes Building a local reverse HTTP/HTTPS proxy with allowlists, terminal prompts, and an LLM advisor hook is easily achievable with standard Node/Go/Python proxy libraries.
Discussion
6 comments analyzed.
Competitors mentioned: Docker Sandboxes
Concerns raised: LLM-only with no tool/action capabilities, Advisor prompt injection vulnerability risk, Website/README written entirely by Claude, not trustworthy, Advisor LLM might make unauthorized calls
Competitors
Other products that read as similar to this one — 213 launches clear the similarity bar, closest 8 shown.
Attention rank: #88 of 214 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 258 days after the earliest competitor.
- I built a firewall for agents because prompt engineering isn't security · hn · 2026-01-19 · 7 upvotes · similarity 0.52
- FireClaw · hn · 2026-03-17 · 5 upvotes · similarity 0.44
- Netfence · hn · 2026-01-25 · 58 upvotes · similarity 0.44
- Armour · hn · 2026-01-20 · 23 upvotes · similarity 0.44
- Fence · hn · 2026-01-20 · 78 upvotes · similarity 0.44
- Turn wire protocols into structured statements LLMs can understand · hn · 2026-09-10 · 6 upvotes · similarity 0.43
- Tui2web · hn · 2026-09-25 · 7 upvotes · similarity 0.42
- Agent-of-empires: opencode & claudecode session manager · hn · 2026-01-10 · 8 upvotes · similarity 0.42
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.