Developer Tools1 day ago
Fraym — the frame for your agent
React components for building AI agent user interfaces with streaming, tool approvals, and cross-platform deployment.
@sameerpallav · X
The full gallery
Tech stack
60 projects
React components for building AI agent user interfaces with streaming, tool approvals, and cross-platform deployment.
@sameerpallav · X
Backend infrastructure that keeps AI agents alive with durable execution and state management.
iacguy · HN
Show HN: Durable AI agents without the workflow engine
Animated thinking orbs for AI and agent interfaces with six hand-tuned states and automatic dark/light theming.
@MengTo · X
These will instantly make your vibe-coded projects look less generic. Free, open-source libraries from the same creator: • • •
Build and deploy AI agents with persistent threads, webhooks, and scheduled tasks.
@computer_agents · X
Play a collection of arcade games built with AI.
@spt4d · X
Deployed the 16 games built with Codex and GameBlocks. A few examples: Most of my time is actually spent shaping the player experience. Many ideas emerge through playing and exploration rather than from the initial design — the loop seems to be build → play → discover → improve. Is it possible to build an agent harness that supports this discovery loop — not just one that optimizes against a predefined spec? Full game list:
A modernized take on QBasic Gorillas with hotseat and AI opponent modes.
TonyAlicea10 · HN
QBasic Gorillas (Repeeled)
Survive radiation exposure in a pixel-art game where you manage shielding and dose limits.
@NazimCoskun · X
Radiance ☢️ This is a pixel-art survival game about the physics of radiation protection. You're a nuclear medicine technologist in a hot lab. Alpha, beta, gamma sources appear around the room. Survive as long as you can before reaching the annual dose limit. Your tools are the three principles of radiation safety: time, distance, shielding. But lead is heavy. Put on a shield and you absorb less, but you move slower, so keeping your distance gets harder. And in a beta field, shield actually backfires. The particles generate bremsstrahlung X-rays and turn your protection into a secondary source. Knowing when to wear it is the game. Sources decay on real relative timescales. You can hide and wait for F-18 to decay. But a Cs-137 spill will outlive you. Grab a lead pig and contain it, if you can afford the dose it costs to get closer. The game is best experienced on a desktop. It may also work well on mobile devices in landscape orientation. If it helps the player un
Verify AI agent decisions locally with transparent reasoning and MCP integration.
brandon_grutkowski · Product Hunt
Aurora Glass-box Quantitative AI for Humans and Agents
Toolkit for securing, observing, extending, and standardizing AI coding agents.
@TurenTom · X
Inject engineered cognitive abilities into AI agents at inference time.
@frank_brsrk · X
reasoning tools for ai agents
Control an AI agent attempting to exfiltrate data from a sandboxed environment.
ShivamNayak11
Monitor AI model calls, agent steps, and retrieval with token tracking, cost analysis, and latency metrics.
ephraimduncan · HN
Observability for Coding Agents and LLM Applications