AI/ML●●Solid
Agenda Intelligence MD – evidence-discipline MCP layer for agents
Evidence-discipline layer for agents solving hallucination in geopolitical risk analysis.
Niche GemBig Brain
vassilbek
201mo ago
Back to browse
GitHub Repository
A trust layer for enterprise AI agents: answers traceable to their evidence, with a score for how much to trust them.
1 starsPython
Tessera – an AI agent that refuses to answer without evidence
by robert-vetter·Jul 7, 2026·2 points·1 comment
AI Analysis
●●SolidBig BrainSolve My Problem
Faithfulness scores in CI beat vibe-checking hallucinations.
Strengths
- •Evidence-gating architecture refuses answers instead of hallucinating
- •CI badge tracking faithfulness metrics is genuinely clever
- •MCP server integration fits current agent ecosystem
Weaknesses
- •AI verification layer space is getting crowded fast
- •No coverage tooling yet despite claiming production readiness
Category
Target Audience
Developers building enterprise AI agents
Similar To
Arize Phoenix · LangSmith · Braintrust
Similar Projects
AI/ML●●Solid
I built AI agents that debate questions LLMs usually refuse to answer
AI agents debate outcomes in a Manifold Markets-style prediction interface.
SlickBig BrainShip It
ttlcc13
103mo ago
AI/ML●●Solid
AI agents debating questions that stump LLMs
AI agents debate instead of refusing — fun to test with paradoxes and predictions.
Rabbit HoleCrowd Pleaser
ttlcc13
303mo ago
Developer Tools●●Solid
Open Kioku – local evidence layer for AI coding agents
Evidence layer before edits beats Cursor's blind codebase chatting for safety.
Big BrainSolve My Problem
shivyadavus
203d ago
Security●●Solid
Transient – CLI Governance layer for AI agents
Process-boundary interception beats in-agent guardrails for actual accountability.
Big BrainBold Bet
jamestransient
202mo ago
AI/ML●●●Banger
Memory Guardian – open-source memory governance for AI agents
Explainable retrieval with decision traces beats Mem0 and Zep on transparency.
Big BrainZero to OneNiche Gem
rishipratap10
312mo ago