Skip to content
#

zero-llm

Star

Here are 4 public repositories matching this topic...

Language: Python
Filter by language
All 8 Python 4 TypeScript 3 Rust 1

hermes-labs-ai / lintlang

Star 45

lintlang is a static linter for AI agent configs, tool descriptions, and system prompts that runs zero-LLM quality gating in CI. Catches language-level failures (vague tool descriptions, missing stop conditions, schema gaps) before they reach runtime, with deterministic regex + structural detectors and no model calls.

linter static-analysis ci-cd developer-tools ai-safety ai-agents quality-gate llm prompt-engineering llm-ops llm-safety system-prompts ai-audit ai-reliability agent-config prompt-linter tool-descriptions zero-llm hermes-labs agent-linter
  • Updated Jun 22, 2026
  • Python

neomatrix369 / rag-params-finder

Sponsor
Star 12

RAG parameter sweep experimentation tool — systematically evaluate vector databases, embedding models, chunking strategies, and retrieval methods using any Vector database. Supports both Voyage AI (hosted) and local sentence-transformers models.

evaluation embedding-models hyperparameter-tuning similarity-score rag vector-search pre-evaluation rag-optimization retrieval-optimization no-mcp zero-llm no-agents relevancy-score chunking-strategies
  • Updated Jun 9, 2026
  • Python

Bryanh9111 / Engram

Star 1

Persistent memory MCP server for AI coding agents like Claude Code. Zero-LLM, local-first (SQLite + FTS5), proactive recall by file path. 12 MCP tools, 113 tests. The MEMORY.md alternative that stays constant-cost at 10,000+ memories.

python memory sqlite mcp developer-tools persistent-memory knowledge-base ai-agents fts5 local-first second-brain anthropic-claude llm-memory ai-memory model-context-protocol mcp-server agent-memory claude-code proactive-recall zero-llm
  • Updated Jun 22, 2026
  • Python

hermes-labs-ai / fidelis

Star 0

fidelis is zero-LLM agent memory for Claude Code and AI agents: a local-first memory layer whose default retrieval path uses BM25, dense vectors, and reciprocal rank fusion with no LLM call. It returns your original passages verbatim instead of paraphrasing and runs fully local. Benchmarked on LongMemEval-S. MIT, by Hermes Labs.

retrieval mcp bm25 fidelity ai-agents rag local-first llm llm-memory agent-memory claude-code longmemeval ai-reliability zero-llm hermes-labs
  • Updated Jun 22, 2026
  • Python

Improve this page

Add a description, image, and links to the zero-llm topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the zero-llm topic, visit your repo's landing page and select "manage topics."

Learn more