Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
An on-call agent that can't lie to itself. Its memory and its actions commit in the same transaction, or neither happens.
An AI medication-safety agent that goes back and un-says what it told you. When the FDA escalates a recall, it finds every patient it already reassured and corrects them by name, in seconds.
When one agent's commit invalidates another's plan, INTERLOCK finds which steps actually died and redoes only those. Semantic concurrency control for parallel agents, built on CockroachDB.
Matches company projects with candidates using genuine passion signals from GitHub, Devpost, Kaggle, lablab.ai, portfolios, and public projects instead of resumes.
AI agent with PROPOSE/DECIDE governance — every action requires human authorization, every decision persists as searchable institutional memory in CockroachDB on AWS.
Your AI tutor's memory can't afford to forget a student mid-lesson. CockroachDB gives it memory that survives node failures—zero data loss, no stale reads, proven live.
Three agents. One shared brain. No agent left behind.
Precedent is a video triage agent for robot fleets: it watches footage it has never seen, files what each clip is, and escalates to a human only when its own past decisions do not answer the question.
An agentic memory engine that turns incident outcomes into durable, evidence-cited knowledge — making every future response sharper.
A real-time truth layer that stops AI agents from acting on stale, superseded, or revoked memories by revalidating critical memory at commit time.
transactional memory engine for ai agents
Every permit system gates on the present; MAINLINE gates on ancestry — the database refuses the merge until someone signs against the incident that wrote the rule.
Self-learning support agent with persistent memory powered by CockroachDB
CockroachDB-powered coordination for safe, parallel AI changes across microservices.
VeriMemory is a trusted memory layer for AI that makes every stored memory verifiable, tamper-evident, and grounded—so AI can remember what actually happened, not just what it thinks it remembers.
"Survivable, hygienic agentic memory: an incident-response agent whose memory survives a full region failure and audits every write it lets in — on CockroachDB + Bedrock."
Remember before you place a trade
CockroachDB remembers. HIOP decides. Memory never becomes authority.
Most tools warn you about a migration. We run it somewhere safe first, score the forecast, and remember the lesson so the next one is not a cold guess.
Durable shared memory for AI coding agents on CockroachDB, with provable forgetting: erase one client and get a signed certificate anyone can verify against the live cluster.
Humanitarian data protection intelligence.
Case Match finds precedents across industries by structure, explains why they transfer, drafts pitch language, and remembers every search so firm knowledge compounds.
NMAFC is a biologically inspired, stateful memory system for LLM agents, enabling conversational AI to remember, forget, and prioritize information like human memory.
CortexOps is an AI agent for CockroachDB that autonomously diagnoses incidents using AWS Bedrock, executes gated fixes, and stores decision rationale in distributed vector memory for instant recall.
1 – 24 of 444
