episodaiSAFE
Sovereign local AI agent memory MCP server with SQLite WAL, hybrid retrieval, Obsidian workflows, HTTP bridge, and hardware-aware acceleration.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/lalithbuilds) [](https://github.com/lalithbuilds/alpuris-os)
a276e0532b2bOBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add episodai --env ENGRAM_API_KEY=${ENGRAM_API_KEY} --env TOKENIZERS_PARALLELISM=${TOKENIZERS_PARALLELISM} -- uvx episodai{
"mcpServers": {
"episodai": {
"command": "uvx",
"args": [
"episodai"
],
"env": {
"ENGRAM_API_KEY": "${ENGRAM_API_KEY}",
"TOKENIZERS_PARALLELISM": "${TOKENIZERS_PARALLELISM}"
}
}
}
}Exposed tools (2)
1 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
ingest_obsidian | read | Ingest an entire Obsidian markdown vault into the knowledge graph and vector store. |
save_memory | write | Save a new memory node with dense vector embedding, category, importance, project namespace, and conflict detection. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (3 observation(s))
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (4)
h = int(hashlib.md5(tok.encode("utf-8")).hexdigest(), 16)return hashlib.md5(p.read_bytes()).hexdigest()
BASE_URL = f"http://127.0.0.1:{TEST_PORT}""text": "Ensure Python uv is installed via curl -LsSf https://astral.sh/uv/install.sh | sh or brew install uv.",
Gates applied: no_behavioural_pass.
a276e0532b2bfull audit observations/trust-audit/mcp-server/lalithbuilds__episodai.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | a276e0532b2b | SAFE | B | 89 | first audit |
Questions
What is the episodai MCP server?
Sovereign local AI agent memory MCP server with SQLite WAL, hybrid retrieval, Obsidian workflows, HTTP bridge, and hardware-aware acceleration.
What tools does episodai expose?
2 in total: 1 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is episodai safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does episodai need?
It reads ENGRAM_API_KEY and TOKENIZERS_PARALLELISM from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (a276e0532b2b), read on 2026-10-11. The repository is watched and re-audited when it changes.