by hermes-labs-ai · MCP Server · ★ 20
Agent memory without the retrieval tax. Fidelity-preserving memory for Claude Code and AI agents — local-first, fast, and with no LLM in the default retrieval path. 83.2% R@1 on LongMemEval-S, $0/query retrieval.
| Stars | 20 |
| Forks | 1 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 53.4255964988788/100 |
| Last Updated | 2026-05-28 |
| Created | 2026-03-27 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~93k |
Explore other popular mcp server tools:
fidelis is Agent memory without the retrieval tax. Fidelity-preserving memory for Claude Code and AI agents — local-first, fast, and with no LLM in the default retrieval path. 83.2% R@1 on LongMemEval-S, $0/quer. It is categorized as a MCP Server with 20 GitHub stars.
fidelis is primarily written in Python. It covers topics such as agent-memory, ai-agents, chromadb.
You can find installation instructions and usage details in the fidelis GitHub repository at github.com/hermes-labs-ai/fidelis. The project has 20 stars and 1 forks, indicating an active community.
fidelis is released under the MIT license, making it free to use and modify according to the license terms.