HN Showcase
Back to browse
GitHub Repository

Open-source Prompt Firewall — deflect up to 95% of redundant LLM traffic before it leaves your infrastructure. Documents: https://isartor-ai.github.io/Isartor/index.html

21 starsRust

Isartor – Pure-Rust prompt firewall, deflects 60-95% of LLM traffic

by zippode·Mar 27, 2026·3 points·1 comment
Visit ProjectView on HN

AI Analysis

●●●BangerSolve My ProblemSlick

Local semantic caching cuts LLM costs without changing your code.

Strengths
  • •Pure Rust single binary means no runtime dependencies to manage.
  • •Integrates directly with Copilot and Cursor via simple proxy config.
  • •Embedded SLM routing offloads trivial queries before they hit paid APIs.
Weaknesses
  • •Semantic caching accuracy depends on embedding quality, might miss nuanced context.
  • •No Windows installer provided yet, only macOS and Linux scripts.
Target Audience

Developers using LLM APIs (Cursor, Copilot, Claude)

Similar To

Helicone · Portkey · CacheLLM

Similar Projects

Security○Pass

ClawShield – Open-source firewall for agent-to-agent AI communication

This feels like the first serious attempt to treat agent-to-agent chatter as a network security problem: 16+ prompt-injection signatures (with recursive base64 decoding), AST static analysis of skills via acorn/estree, and sandboxed dynamic checks are concrete, non-trivial defenses. The repo shows real engineering (Docker, CI, security scans, 181 tests) — the missing piece is real-world performance and adoption, but if you run agent fleets this is worth poking at.

WizardryNiche Gem
Joe_DNAI
225mo ago
AI/ML●●Solid

Mnemo – local-first AI memory layer for any LLM (Rust, SQLite,petgraph)

Knowledge graph memory beats pure vector search, but Mem0 and LangChain already own this space.

Big BrainShip It
zaydmulani
60311mo ago
Security●●●Banger

OpenGuard

Drop-in LLM traffic guard with PII redaction and prompt injection detection, one command.

Solve My ProblemSlick
everlier
104mo ago