Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

How to build and self-host a code review agent

Details

External ID
49128177
Source
HN
Company
—
Product
How to build and self-host a code review agent
Website domain
trytilde.ai
Launched
July 31, 2026
Cohort
—
Upvotes
29
Upvotes percentile
0.7789725209080047
Tags
—
Fetched at
Sept. 10, 2026, 5:32 a.m.
Updated at
Sept. 10, 2026, 5:32 a.m.

Description

Hey HN,I've had a side-project that I've slowly ticked away at over the last year called Tilde. Tilde is a harness SDK platform - I've tried to take the best things of OpenClaw, Hermes & other harnesses and decompose them and make them available as cloud API building blocks.You can use Tilde to create AI agents for your use case, fast and self-host the agent's yourself.The documentation (and attached blog post) leave a lot to be desired in terms of technical documentation but hopefully the attached git repo does a good job of showcasing the API.https://github.com/trytilde/examples

Enrichment

Theme
developer tools for AI agents
Vertical
Horizontal
Function
Agent / copilot
Audience
Developer
AI stance
AI-native
Project type
Hobby / open-source project
Normalized one-liner
guide to building and self-hosting code review agents
Manually corrected
False

Could you build this?

Partial While basic agent loops and GitHub PR webhook wrappers are simple to code, a multi-tenant cloud agent platform managing isolated MCP servers, secure credential vaults, and bidirectional proxy infra requires dedicated cloud infrastructure engineering.

What it would actually take: Tilde's backend architecture requires an orchestrator managing sandboxed container runtimes (such as Firecracker microVMs or isolated containers) to run arbitrary Model Context Protocol (MCP) servers safely. Hard challenges include real-time bi-directional HTTP/2 reverse-proxying, zero-trust credential encryption and identity management (IAM) across dynamic tools, and managing persistent memory retrieval across agent turns. Building it reliably requires expert cloud systems engineers experienced in Kubernetes/virtualization, microservices security, and LLM orchestration.

Discussion

6 comments analyzed.

Competitors mentioned: lm-studio, OpenRouter, Claude Code, Reticle MCP server

Concerns raised: Self-hosting models is very fiddly, Dependency on frontier labs (Anthropic/OpenAI)

Feature requests: Support for open source models instead of Anthropic/OpenAI, Integration with Reticle for agent coding work verification

Competitors

Other products that read as similar to this one — 310 launches clear the similarity bar, closest 8 shown.

Attention rank: #65 of 311 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 269 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a agent / copilot tool for Agriculture yet.