Nicheloom

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

OnPanda

Steer LLMs and agents at the token level

Details

External ID
49759013
Source
HN
Company
—
Product
OnPanda
Website domain
diyer22.com
Launched
Sept. 18, 2026
Cohort
—
Upvotes
5
Upvotes percentile
0.12998405103668262
Tags
—
Fetched at
Sept. 22, 2026, 5:02 p.m.
Updated at
Sept. 22, 2026, 5:02 p.m.

Description

I built onPanda – an interactive tool for token visualization & control, model inspection and data annotation.onPanda is designed for hackers, power users, curious minds, and engineers. Its UI is built for deep exploration and efficient data annotation.- The core loop is simple: hover over a token → click an alternative or edit freely → continue generation. You can edit every part of model output exposed by onPanda, including reasoning and tool calls.- Edit prompts directly, branch tool calls, and use a tree structure to record branch history. This makes onPanda useful for model inspection and prompt engineering.- Support multiple modalities, including images, video, and audio; use tool calls and connect MCP servers to perform tasks in real environments.- Connect popular harnesses such as Claude Code, Codex, and OpenCode to execute tasks. Explore and compare their tool sets, system prompts, skills, and memory mechanisms.- onPanda includes a built-in browser-agent, an agent that runs in the user's browser without installation. It uses the browser as its harness and provides JavaScript execution, information retrieval, interface interaction, multimedia I/O, local file access, and persistent memory.- onPanda stands for on-Policy Alignment Data Annotator. - As an annotation tool, onPanda efficiently labels on-policy data. Its token-level correction format also provides fine-grained supervision with precise positions and naturally paired positive–negative samples. - We believe these unique properties will make token-level correction a highly efficient and practical paradigm for future LLM alignment. - Our paper and benchmark for token-level correction: https://on-panda.github.io/research/ I have been building onPanda since Sept 2024, and it took two years for it to gradually enrich its functionality and ease of use. Any feedback and evaluation are welcome.Try it online (works on mobile): https://onpanda.diyer22.com/GitHub repo for self-hosting: https://github.com/on-panda/on-pandaDetailed introduction on X: https://x.com/diyerxx/status/2101020850405462041

Enrichment

Theme
browser automation and scraping for AI
Vertical
Horizontal
Function
Model & infra
Audience
Developer
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
token-level steering for language models
Manually corrected
False

Could you build this?

Yes An interactive web UI to inspect model logits, hover over tokens, and tweak generation parameters via standard LLM API logit bias or open model endpoints is well within vibe-coding scope.

Discussion

No comments on this launch.

Competitors

Other products that read as similar to this one — 12 launches clear the similarity bar, closest 8 shown.

Attention rank: #11 of 13 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 281 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a model & infra tool for Fintech yet.