Home › Knowledge & Memory › Perenna
Perenna
A lightweight, Git-backed permanent memory for AI agents.
Connect
Review any command before running it. Package names and URLs come from the server's own registry entry.
Package (pypi 0.4.1)
uvx perenna
Or add to your MCP client config:
{
"mcpServers": {
"perenna": {
"command": "uvx",
"args": [
"perenna"
],
"env": {
"VEXOR_API_KEY": "<YOUR_VALUE>",
"VEXOR_REMOTE_RERANK_API_KEY": "<YOUR_VALUE>"
}
}
}
}
PERENNA_GIT_REMOTE— Git remote name used for optional synchronization (for example, origin); leave unset for local-only operationVEXOR_API_KEYsecret — Embedding provider API key (optional; overrides a stored key; providers can also be configured via `vexor init`)VEXOR_REMOTE_RERANK_API_KEYsecret — Remote reranker API key (optional; overrides a stored key; only needed when rerank is set to remote)VEXOR_CONFIG_JSON— Non-secret Vexor config as a JSON object, e.g. {"provider": "gemini", "rerank": "bm25"} (optional; merged over ~/.vexor/config.json; credential fields are rejected, use the dedicated variables)
This server takes extra arguments — see its repository.
Related servers
Context7
Up-to-date docs for AI agents
mempalace/mempalace
The best-benchmarked open-source AI memory system. And it's free.
hindsight
Hindsight: long-term memory for AI agents modeled on human memory.
cognee
Memory manager for AI apps and agents using graph and vector stores, with ingestion from many data sources.
Skill_Seekers
Turn docs, GitHub repos, PDFs, videos, Confluence, Notion and Slack/Discord into AI skills and RAG knowledge, exportable to vector…
basic-memory
Local-first knowledge management with bi-directional LLM sync via Markdown files.
Data from the Official MCP Registry