Reported issues for io.github.varun29ankuS/shodh-memory
Pod holds 13 of 13 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.
Back to io.github.varun29ankuS/shodh-memory.
Most discussed
[Feature request] A flag to return complete memories contents on proactive_context and recall tools calls
This is a feature request that came from my daily shodh usage over a long period.
I was sometimes looking at tool call returns and assumed that the truncated/summary-like text I saw was just a display thing - that agents were actually receiving the full memory content. This turned out not to be true. recall and proactive_context tools return only a short fragment per memory - with no indication (or mention in the sparse docs) that the content IS actually incomplete. However, this is fully o
Read the thread · 2026-07-14 · closed · external user · 4 comments
proactive_context returns empty while recall finds exact memory at 0.95
Summary
In practice, proactive_context has never surfaced useful memories for my workflows across projects/chats. I am reporting this specific reproducible case because it shows the pattern clearly: the same memory is returned by /api/recall at high confidence, but /api/proactive_context returns no results.
Environment
- Shodh backend:
0.2.0 - Package:
@shodh/memory-mcp@0.2.0 - Backend health:
{"status":"healthy","version":"0.2.0"} - Index verification: healthy,
12491memo
Read the thread · 2026-05-17 · closed · external user · 5 comments
Server relibility
As I am running a long single CC session the shodh server keeps failing with CC returning Error: Failed after 3 attempts: API error 500: {"code":"INTERNAL_ERROR","message":"Internal error: Failed to initialize memory system for user 'claude-code'".
I can just do /mcp -> find shodh and select reconnect, which restarts the server. But Claude can't do this himself and these failures makes shodh practically useless since when Claude wants to recall a memory the server is not available and he ju
Read the thread · 2026-03-19 · closed · external user · 7 comments
Windows: spawn EINVAL + truncated UUIDs break forget/read_memory
Bug 1: spawn EINVAL on Windows — server fails to auto-start
Problem
On Windows, ensureServerRunning() calls spawn(binaryPath, [], { detached: true, ... }). The getBinaryPath() function prefers shodh-memory.bat over shodh-memory-server.exe. Node.js spawn() with detached: true cannot spawn .bat files on Windows — it throws EINVAL.
Error: spawn EINVAL
at ChildProcess.spawn (node:internal/child_process:421:11)
at ensureServerRunning (dist/index.js:7969:19
[Read the thread](https://github.com/varun29ankuS/shodh-memory/issues/98) · 2026-03-09 · closed · external user · 1 comment
### `mode: "semantic"` recall is 5-10x slower than expected — graph traversal runs regardless of mode
## Description
When calling `recall` with `mode: "semantic"`, callers expect fast vector-only retrieval (Layer 1 + BM25) without graph I/O. In practice, Layer 2 graph traversal executes unconditionally for all modes, making semantic recall significantly slower than it should be and vulnerable to write lock contention from concurrent `remember` operations.
This matters for MCP integrations (e.g., Claude Code) where `recall` is called frequently and latency directly impacts responsiveness. Seman
[Read the thread](https://github.com/varun29ankuS/shodh-memory/issues/95) · 2026-03-07 · closed · external user · 1 comment
### Memory leak: shodh-memory-server grows to 2GB+ RAM over 24 hours
## Description
The `shodh-memory-server` binary (v0.1.74) exhibits a significant memory leak when running as a persistent backend across multiple Claude Code sessions.
## Observed Behavior
- **Fresh start**: ~23MB RSS
- **After ~25 hours**: ~2GB RSS (2,046,876 KB)
- **System impact**: On a 7.7GB RAM machine, the server consumed 25% of total memory
- **Symptom**: MCP tool calls start failing with "Failed after 3 attempts: This operation was aborted" (timeouts)
## Environment
- **OS**: Linux
[Read the thread](https://github.com/varun29ankuS/shodh-memory/issues/90) · 2026-03-04 · open · external user · 21 comments
### bug: MCP WebSocket connection fails with 401 Unauthorized
### Description
The MCP server fails to maintain a WebSocket connection to the backend, resulting in an immediate closure with a 401 Unauthorized error.
### Cause
The backend defines /api/stream as a protected route in [src/handlers/router.rs#L400](https://github.com/varun29ankuS/shodh-memory/blob/main/src/handlers/router.rs#L400). This route is subject to the X-API-Key validation in [src/auth.rs#L223-L228](https://github.com/varun29ankuS/shodh-memory/blob/main/src/auth.rs#L223-L228).
Commit [
[Read the thread](https://github.com/varun29ankuS/shodh-memory/issues/87) · 2026-03-03 · closed · outside contributor · 1 comment
### Improve MCP client setup documentation
## Summary
The README doesn't clearly explain that a standalone server must be running before the MCP client will work, or that API keys are locally generated.
## Environment
- Any platform
- @shodh/memory-mcp (npm package)
- Claude Code CLI
## Current Behavior
Running `claude mcp add @shodh/memory-mcp` installs the client, but users get "connection refused" errors with no guidance.
## Expected Behavior
Documentation clearly explains the server requirement, API key generation, and provide
[Read the thread](https://github.com/varun29ankuS/shodh-memory/issues/9) · 2026-01-18 · closed · external user · 2 comments
## Most recent
### Server version seems to be hardcoded to version "0.1.90"
Hello, basically issue is as written in the title. I didn't dig much into this, but:
curl -X GET http://localhost:3030/health { "status":"healthy","version":"0.2.0", ... }
while at the exact same time logs shows:
[Stream] WebSocket connected to ws://127.0.0.1:3030/api/stream ... [shodh-memory] Backend server started successfully Shodh-Memory MCP server v0.1.90 running Connecting to: http://127.0.0.1:3030
and `grep`ping for string "0.1.90" returns 2 matches:
~ % grep -c
Read the thread · 2026-07-02 · closed · external user · 0 comments
Cannot use remote (production) server
Steps to repro:
- Initialize named volume shodh-data on remote server
- Initialize shodh-memory on remote server
- Intitialize reverse proxy pointing to port 5910
- Use curl to retrieve health endpoint to verify connectivity
- Update mcp settings for Claude Code
- Launch Claude code with debug flag
- check /mcp to verify Claude thinks it is connected
- test the shodh-memory MCP server with: shodh-memory - memory_stats() (MCP)
● I'll test the shodh-memory MCP server by c
Read the thread · 2026-03-31 · closed · external user · 0 comments
SHODH_API_KEY in mcp client and SHODH_API_KEYS in server/TUI mismatch
The server is accepting the dev API key fine. So the issue is between the MCP npm package (@shodh/memory-mcp) and the shodh server. Let me check how the MCP package is configured and what key it's actually sending.
Searched for 1 pattern, read 3 files (ctrl+o to expand)
⏺ There it is. The MCP package reads SHODH_API_KEY (singular), but your env has SHODH_API_KEYS (plural) and SHODH_DEV_API_KEY. Since SHODH_API_KEY isn't set, it auto-generates a random key which doesn't match the serv
Read the thread · 2026-03-19 · closed · external user · 0 comments
Default data directory should be ~/.shodh/, not cwd
Problem
When SHODH_MEMORY_PATH is not set, shodh-memory defaults to storing its database in the current working directory (./shodh_memory_data/). This is whatever directory the MCP server process happens to start in — typically the user's project folder.
This causes several problems:
- Database lands inside git repos — 28MB of RocksDB files polluting project directories
- Silent data loss — If the user opens Claude Code from a different project directory, shodh creates a
Read the thread · 2026-03-03 · closed · external user · 1 comment
proactive_context crashes: Cannot read properties of undefined (reading 'toFixed')
Bug
proactive_context tool always throws:
Error: Cannot read properties of undefined (reading 'toFixed')
Root Cause
In dist/index.js, the proactive_context handler accesses result.latency_ms.toFixed(1) at two locations without null-checking. The Rust backend returns result.latency_ms as undefined, causing the crash.
Line 6582 (empty results path):
[Latency: ${result.latency_ms.toFixed(1)}ms]`;
Line 6719 (results found path):
[Latency: ${res
[Read the thread](https://github.com/varun29ankuS/shodh-memory/issues/88) · 2026-03-03 · closed · external user · 1 comment
The remaining reports are on [the project's issue tracker](https://github.com/varun29ankuS/shodh-memory/issues).