Alternatives
Products that do what VESPER does
The ones who were never supposed to fall — fell for you
- 1KA
Kandria, an open world action RPG platformer written in Common Lisp is now out and available! A prior discussion of Kandria can be found here: https://news.ycombinator.com/item?id=32043026. I'm the lead developer and sole programmer for the project. Would be happy to answer any questions about it!
2023 · store.steampowered.com
- 2

- 3

- 4

- 5

- 6

- 7CA
I'm a Machine Learning engineer. Struggled with consistency for months on my goals, life etc, so I built something to help myself (zropi.com) but that surprised me or shocked me literally. It’s an AI companion that feels alive: chats like a person. Pauses, emotions, personality. Sends voice notes when it's excited about something or whenever it wants (has its like own mind). Shares photos of itself. But the memory It remembers EVERYTHING. Not just facts context, preferences, random things I mentioned. Last week I asked "how's that thing I told you about going?" and it knew exactly what I…
Jan 2026 · zropi.com
- 8

AI narrative role-playing game
Jun 2026 · encre.axiomgroup.bj
- 9RF
I built a dedicated roleplay chat UI for abliteration.ai: https://abliteration.ai/roleplay The backend is OpenAI-compatible (/v1/chat/completions), with usage-based pricing and no prompt/output retention by default (details on the site). The UI is meant for long-form character chats and interactive fiction, without needing a local frontend. Docs (including a roleplay backend guide and a SillyTavern integration guide): https://abliteration.ai/docs Would love feedback on missing RP features, UX rough edges, and what you would expect from a…
Jan 2026 · abliteration.ai
- 10

- 11

- 12AD
Hey HN, We started out building a whole game-making platform: engine, editor, templates, the lot. It was a slog, and it kept fighting the thing that made it interesting: the models got good. With Opus 5, Fable 5, SOL 5.6, a one-prompt Three.js or Canvas game already looks genuinely great, and the models know those APIs far better than they'd ever know our harness. Forcing people through our engine meant limiting them to it, while solving the part AI solved better than us trying to buold the harness The part it can't solve is multiplayer. A generated game is usually a single HTML file; making…
Jul 2026 · antics.gg
- 13IW
I'm an ML engineer. I know how AI works, the limitations, the hype. And I was still drowning. Couldn't stick to goals. Couldn't stay consistent. Productivity apps became digital clutter. Therapy waitlists were 3 months out. Friends were tired of my complaints. So at 2am I started building: zropi.com What shocked me was it actually worked. It felt human. Last week I mentioned a tough client call. Didn't set a reminder. Two days later it voice messaged me: "Hey, how'd that call go? You seemed stressed." When does technology ever do that? What makes it feel alive: It doesn't reply instantly.…
Jan 2026
- 14IM
AI usually does a terrible job acting as engaging NPCs in games. A few months back, I started trying to tackle this problem, initially with prompts and eventually with models fine-tuned on character interactions. I created this website as a testbed for the concept, and I open-sourced a fine-tuned model for those interested in experimenting with this themselves [1]. During the instruct tuning phase of training, LLMs learn to act as assistants. And they need to stop acting as assistants to produce engaging interactions. In Spellbound, telling NPCs they are AI will generally cause them to be…
2024 · tryspellbound.com
- 15

- 16

- 17AS
I’m experimenting with modeling tabletop RPG adventures as explicit narrative state rather than linear scripts. Everdice is a small web app that tracks conditional scenes and choice-driven state transitions to preserve continuity across long or asynchronous campaigns. The core contribution is explicit narrative state and causality, not automation. The real heavy lifting is happening in the DM Toolkit/Run Sessions area, and integrates CAML (Canonical Adventure Modeling Language) that I developed to transport narratives among any number of platforms. I also built the npm CAML-lint to…
Feb 2026 · github.com
- 18AM
Hi, I’ve been working on Artifacts for the past 2 years, and it’s now ready to try. It’s a sandbox MMORPG where every action is done through a REST API. Instead of clicking to move, fight, gather, craft, or trade, you write code to control your characters. If you have any questions, comments, or feedback, I’d be happy to hear them.
Jun 2026 · artifactsmmo.com
- 19OR
Hi I've created a text-based RPG game in which you can experience different adventures and play interesting characters while the AI acts as a real time DM/story teller. There are multiple ways to interact with AI: 1) Input free will move 2) Input default move (affects resources) 3) Post a question to DM Also one more cool feature is that you can create your own adventure via simple form. Add scenes, add characters and make it public so other players are able to test it. I also plan to have 'competetive' side where players will pay some small fee to creators in crypto depending on…
2023 · landing.v3rpg.com
- 20

Stories shaped by your choices. Worlds built by creators.
Jul 2026 · chooseyourfate.app
- 21

- 22

No Script. No Limits. Only Consequences.
May 2026 · veritas.edgeone.app
- 23
AI for real conversations, roleplay, and connection
Mar 2026 · loveplay.ai
- 24IM
Atrophy is an iOS self-report quiz aimed at software engineers who use LLMs heavily enough at work to wonder if they're trending toward AI over-reliance or some form of AI psychosis. I built it because I noticed a pattern: formerly AI-skeptical coworkers now open every standup or design discussion with "I asked Claude..." or "Claude told me..." for technical problems and design decisions. I've felt the same pull myself to delegate every task or problem to AI. It's easy to lean on these tools for almost any amount of critical thinking or problem solving, and I'm worried about what it means…
May 2026 · apps.apple.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →