This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
onPanda
Inspect and steer LLMs and agents at the token level
onPanda is an open-source interface for inspecting and steering LLMs and agents at the token level. Select a generated token, inspect alternatives, replace it or edit freely, then continue generation from that point. Branch generations, inspect reasoning and tool calls, and annotate model and agent trajectories in one interactive workspace.
I started building onPanda in 2024, and over the past two years it has gradually grown into a workspace for deeply exploring, steering, and annotating LLMs and agents.
The core interaction is simple: when you want to change where a generation is heading, select a token, inspect its alternatives or edit it freely, and continue generation from that point. This makes it easy to see how a small intervention can change everything that follows.
I wanted this interaction to work beyond normal chat output. In onPanda, you can do token-level correction directly inside the generated text, including reasoning and tool calls, while keeping branches and their history. You can also connect tools, MCP servers, and agent harnesses such as Claude Code, Codex, and OpenCode to inspect and modify more complex agent trajectories.
The name "onPanda" originally comes from "on-Policy Alignment Data Annotator." Data annotation is still an important part of the project: token-level corrections can produce precise supervision while keeping the corrected trajectory close to the model’s own policy. In a small controlled study, this workflow reduced median annotation time by 52% compared with manual post-editing.
But onPanda has grown beyond annotation. I now use it as a general interface for looking inside model generation, experimenting with alternatives, debugging agent behavior, and understanding what changes when you intervene at a particular point.
The project is fully open source and self-hostable. I’d love to hear how you would use this kind of interface—especially what you’d want to inspect, compare, or control when working with LLMs and agents.
“Inspect and steer LLMs and agents at the token level”
onPanda was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #110 on the daily leaderboard. onPanda is an open-source interface for inspecting and steering LLMs and agents at the token level. Select a generated token, inspect alternatives, replace it or edit freely, then continue generation from that point. Branch generations, inspect reasoning and tool calls, and annotate model and agent trajectories in one interactive workspace.
On the analytics side, onPanda competes within Open Source, Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how onPanda performed against the three products that launched closest to it on the same day.
Who hunted onPanda?
onPanda was hunted by Lei Yang. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of onPanda including community comment highlights and product details, visit the product overview.
Lei Yang
Hi everyone! 👋
I started building onPanda in 2024, and over the past two years it has gradually grown into a workspace for deeply exploring, steering, and annotating LLMs and agents.
The core interaction is simple: when you want to change where a generation is heading, select a token, inspect its alternatives or edit it freely, and continue generation from that point. This makes it easy to see how a small intervention can change everything that follows.
I wanted this interaction to work beyond normal chat output. In onPanda, you can do token-level correction directly inside the generated text, including reasoning and tool calls, while keeping branches and their history. You can also connect tools, MCP servers, and agent harnesses such as Claude Code, Codex, and OpenCode to inspect and modify more complex agent trajectories.
The name "onPanda" originally comes from "on-Policy Alignment Data Annotator." Data annotation is still an important part of the project: token-level corrections can produce precise supervision while keeping the corrected trajectory close to the model’s own policy. In a small controlled study, this workflow reduced median annotation time by 52% compared with manual post-editing.
But onPanda has grown beyond annotation. I now use it as a general interface for looking inside model generation, experimenting with alternatives, debugging agent behavior, and understanding what changes when you intervene at a particular point.
The project is fully open source and self-hostable. I’d love to hear how you would use this kind of interface—especially what you’d want to inspect, compare, or control when working with LLMs and agents.
Thanks for checking it out 🐼
Try it online (mobile-friendly): https://onpanda.diyer22.com