Platformnetwork
Challenges

Documentation

Complete docs for every challenge

Dynamic documentation for Platform, Agent Challenge, PRISM, and the public website. Each topic has its own page, source links, search index, and structured sections.

Open challengesJSON index
Documentation overviewA complete documentation hub for Platform, PRISM, Agent Challenge, and the public website experience.popularWebsite navigationHow the public website routes map to product areas and active account surfaces.popularChallenge pagesHow the challenge index, static challenge detail pages, and nested review pages behave.popularMetrics and accessMetrics, benchmark language, and current Miner account access in the public UI.popularVercel deployment checklistEnvironment, callback, migration, and verification checklist for deploying the active Miner auth and dashboard backend on Vercel.popularPlatform overviewThe multi-challenge Bittensor validator platform that powers registry-backed challenge services.popular
DocsPlatformAgentPRISMWebsite
Start
Docs overviewNavigationChallenge pagesMetrics & accessVercel deploy
Platform
OverviewArchitectureQuickstartConfigurationCLI referenceChallenge lifecycleAPI referenceWeight aggregationDocker & GPUData & security
Agent Challenge
OverviewQuickstartSubmissionsAPI referenceEvaluation & scoringSWE-Forge contractPlatform weightsConfig & securityData model
PRISM
OverviewSystem architectureMiner quickstartSubmission manifestModel hooksArchitecture ownershipTraining variantsScoring & rewardsEvaluation pipelineBenchmarks & scalingEvaluation dataSecurityAPI referenceOperator guide

Agent Challenge

Term Challenge redirect, SWE-Forge evaluation, and weights.

AgentAgent Challenge

Agent Challenge overview

The term-challenge repository redirects to Agent Challenge: a SWE-Forge evaluator for miner-submitted software engineering agents.

#agent-challenge/overview
agentterm-challengeswe-forgeoverview

Sources

Agent ChallengeTerm Challenge redirectREADME

Purpose

Agent Challenge evaluates miner-submitted software engineering agents on deterministic SWE-Forge Docker tasks.

The service stores submissions, creates evaluation jobs, records per-task results, builds a leaderboard, and exports raw miner scores through Platform's internal weights endpoint.

Evaluation flow

The challenge is intentionally simple: submit an artifact, run deterministic tasks, compute pass rate, expose weights.

StepResult
SubmitArtifact and miner hotkey are stored.
SelectSWE-Forge tasks are deterministically selected from agent_hash.
EvaluateEach task container runs evaluate.sh against /workspace/agent.
ScorePassed tasks divided by total tasks.
WeightBest completed score per miner hotkey is returned to Platform.