Back to browse
NILScript – OpenAPI for agent actions, so hallucinations can't write

NILScript – OpenAPI for agent actions, so hallucinations can't write

by bashierkh·Jun 18, 2026·1 point·0 comments

AI Analysis

●●●BangerBig BrainZero to OneBold Bet

Structural agent safety via wire protocol—0% unauthorized writes across 4,216 injection evals.

Strengths
  • Propose→approve→commit→rollback workflow makes safety structural, not model-dependent
  • Agents can only call verbs the backend explicitly declares—no hallucinated endpoints
  • CLI scaffolds conformant adapters; three files to build, rest is generated
Weaknesses
  • v0.3.0 draft standard—early stage, adoption and ecosystem still unproven
  • Human approval gate may bottleneck fully autonomous agent workflows
Category
Target Audience

Developers building AI agents that interact with databases or backend systems

Similar To

Guardrails AI · Lakera Guard · LangChain Tools

Similar Projects

Developer Tools●●Solid

Turn any OpenAPI spec into agent-callable skills

It extracts focused, executable operations from giant OpenAPI files (the GitHub REST YAML is shown) to shrink context and avoid sidecar adapter sprawl — a pragmatic answer to token bloat and brittle ad-hoc integrations. Useful and concrete: if it actually generates tidy, updateable skill units and runtime hooks it saves a lot of maintenance. That said, the idea competes with existing LangChain/openai-function patterns; the repo will need clear runtime, versioning, and update strategies to feel like more than a nicer converter.

Solve My ProblemNiche Gem
yz-yu
104mo ago
AI/ML●●Solid

OQP – A verification protocol for AI agents

OpenAPI for agent verification with risk scoring before merge — ambitious standardization play.

Bold BetBig Brain
Aamir21
822mo ago
Security●●●Banger

AIP – A Cryptographic Identity Protocol for Autonomous AI Agents

OAuth + TLS for AI agents with Ed25519 identity and global kill switch before agents act.

Zero to OneBig BrainBold Bet
theaniketgiri
113mo ago