Browse applications built on modern technologies. Explore PoC and MVP applications created by our community and discover innovative use cases for modern technologies.
Aura is a sovereign, neuro-symbolic AI operating system that turns natural-language intent into transparent, governed action through local parsing, agent collaboration, bounded experimentation, verifiable learning, and human-controlled decision gates.
self-improving agent factory: Gemma 3 27B on an AMD MI300X attempts a frozen pytest benchmark, an improver rewrites its rules (AGENTS.md), and every update is eval-gated — bad rules auto-revert. Improvement is measured, never self-graded.
Cride is Our Video Crime Detection Model Trained Using VideoMAE and GRU
RE-EVOLVE ON HGI is an Intelligence Operating System that orchestrates multi-agent AI workflows through intent-driven planning, adaptive routing, persistent memory, governance, and specification-driven engineering for heterogeneous AI infrastructure.
A local-first hybrid AI agent that answers tasks with a free on-device model and escalates to paid cloud models only when a calibrated confidence gate says it must — maximum accuracy at minimum token cost.
PreFlight predicts Model training cost, runtime, and GPU compatibility before execution. Saving thousands of dollars in computing and reducing computing power wastage and carbon footprint.
ArchMind transforms any codebase into an intelligent knowledge graph that AI agents can reason over. Developers can explore architecture, analyze dependencies, assess change impact, detect design issues, and generate documentation using natural language.
TokenAgent is an autonomous, token-efficient AI coding agent for VS Code. It uses a ReAct loop and a 4-stage pipeline to surgically edit codebases - slashing API costs, bypassing context limits, and preventing LLM hallucinations.
BandOps is an enterprise-grade command center that replaces siloed human panic with an orchestrated swarm of adversarial AI agents. Powered by Band, it resolves multi-million dollar aviation crises in seconds with immutable human-in-the-loop oversight.
NexusCore is the emergency brake for AI agent teams: a Band-powered governance layer that intercepts risky actions, coordinates nine review agents, requires human confirmation for critical moves, and logs every ALLOW/BLOCK decision.
Cipher is an AI-powered platform that turns complex workflows into intelligent, secure, and automated experiences. Combining adaptive agents with real-time insights, Cipher helps teams work faster, smarter, and more efficiently.
A multi-agent developer platform where 6 specialized AI agents collaborate through Band rooms, learn from every task, and compound intelligence across sessions — turning planning, coding, and reviewing into a visible swarm conversation.
Band agents that remember. Mimir-powered persistent memory gives Planner, Executor, and Reviewer agents shared context across sessions — they recall past decisions, conventions, and lessons so your multi-agent team gets smarter every run.
It is an autonomous GTM intelligence platform that continuously monitors the web for competitor activity, buying signals, and market changes. it transforms live web data into actionable sales insights, competitive battle cards
An agentic AI workspace with voice interaction, live documentation, and Git-style conversation branching. Butler transforms conversations into searchable, evolving knowledge you can revisit, compare, and export.
CouncilOS is a collaborative multi-agent reasoning platform where AI models engage in human-like discussions to critique, refine, and evolve code analysis in real time for more reliable and research-oriented reasoning workflows.
GitHub-integrated AI Agent powered by the Featherless API that autonomously creates, edits, and commits code directly to repositories.
StartME is an AI company OS with 20 specialized agents orchestrated by a CEO agent — handling sales, marketing, finance, legal, DevOps & more. Built solo by a 17-year-old from Lagos. One founder. A full AI workforce.
An enterprise-grade AI contract analysis platform powered by Gemini 2.5 Flash. ContractIQ extracts key clauses, identifies hidden legal risks, flags one-sided terms, and provides an interactive AI attorney chat to review contracts in ~20 seconds.
An AI-powered Repository Intelligence & Change Impact Viewer that analyzes uploaded code repositories, visualizes dependency relationships, enables AI-based repository understanding, and predicts the impact of code changes
Bob native npm package that visualizes IBM Bob’s AI code changes in real time with before/after diffs, execution flow diagrams, and BobShell analysis
VibeCheck scans entire codebases using IBM Bob's full-repo context to detect what no linter can: architectural drift, intent mismatches, semantic duplication, and cascading blast radius - the invisible failures that ship when AI writes 60% of your code.
CodeOrbit AI is an AI-powered repository intelligence platform that helps developers instantly analyze, understand, and interact with GitHub repositories using semantic search, Groq AI, repository analytics, and intelligent code insights.
Stop wasting 43% of your AI tokens on code rework. AgentIQ is an enterprise governance platform that audits repositories and generates deterministic multi-IDE context blueprints, ensuring AI agents like IBM Bob code flawlessly on the very first try.
An enterprise-grade, self-healing security firewall and real-time IDE middleware wrapper that audits AI agent workflows and Model Context Protocol (MCP) tool configurations for intent alignment.
SilentBob is a CLI orchestrator for IBM Bob. It auto-detects Git changes, crafts context-rich prompts to save AI tokens, and runs an auto-healing loop to instantly debug and fix failing unit tests.
AI-powered VS Code extension that visualizes your codebase as an interactive graph with dependency mapping, AI file explanations, and a chat interface for code exploration and editing, powered by IBM Granite.
OpenLook gives coding agents visual unit tests: they record browser sessions, send the video to Gemini, get pass/fail UX verdicts, fix the UI, and rerun until it works.
Code Janitor is an AI-powered code review and refactoring platform that detects bugs, suggests optimizations, visualizes codebases, and provides live previews, built with assistance from IBM BOB, IBM’s AI-powered development assistant.