AI/ML●●Solid
Check whether agent logs are independently verifiable
Ed25519 signature verification in browser solves agent accountability for disputes.
Big BrainZero to One
jithinraj
306d ago
Back to browse
GitHub Repository
Evaluation harness for Apodex-1.0 on public deep-research benchmarks.
80 starsPython
Apodex-1.0 – Deep research with independent verifier (90.3 BrowseComp)
by wuqiaocauc·Jun 9, 2026·1 point·0 comments
AI Analysis
●●SolidNiche Gem
90.3 BrowseComp score with verification-centric model architecture.
Strengths
- •Public benchmark results across four deep-research suites with verifiable numbers
- •Multiple model variants from 0.8B to 35B for different compute budgets
Weaknesses
- •This repo is just the evaluation harness, not the actual model weights
- •Deep research agents already have many competing benchmarks and frameworks
Category
Target Audience
AI researchers evaluating deep research models
Similar To
Gaia Benchmark · AgentBench · WebArena
Similar Projects
Developer Tools●●●Banger
Tracecore: Benchmark AI Agents on Deterministic Coding Tasks
Deterministic agent benchmarking with strict validation—unlike SWE-Bench, measures whether agents actually operate.
Solve My ProblemWizardryNiche Gem
extra_cookin
103mo ago
AI/ML●●Solid
EleutherAI / Lm-Evaluation-Harness
Industry standard benchmark harness refactored with lighter installs and new SGLang support.
Crowd Pleaser
marvinified
1027d ago
AI/ML●●●●Gem
Verified Deep Learning with Lean 4
Formally verifies ResNet and ViT architectures using Lean 4 proofs.
WizardryBig BrainNiche Gem
asparagui
601mo ago
Security●●Solid
A test harness that blocks unsafe AI actions before execution
Deterministic policy matrices block AI agents from executing dangerous API calls.
Solve My ProblemShip It
celestinestudio
202mo ago
AI/ML●●●Banger
OpenCastor Agent Harness Evaluator Leaderboard
263k config search space benchmarked across robot fleets—nothing like this exists for robotics AI.
Zero to OneBig BrainNiche Gem
craigm26
312mo ago