telemem — Watchlist | MCP100 Index

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Recheck a specific changing behavior of github.com/TeleAI-UAGI/telemem: Have MCP write/delete memory operations and external model-provider boundaries changed?

Reviewed Oct 9, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Persistent agent memory and retrieval

What we know

TeleMem ships a standalone MCP long-term-memory server with eight documented tools.

Maintenance / activity evidence

TeleMem v1.10.0 was released 2026-08-15 with DeepSeek Harness MCP integrations.

Tracking evidence observed Oct 9, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Local memory store; memory write/delete and bulk-delete tools exist; provider keys/config can enable external model calls. Writes: Write/update memories; Delete or bulk-delete memory records.
Authentication not yet verified.
Can retain/retrieve agent memories; avoid recording credentials or confidential content without controls.

Can retain/retrieve agent memories; avoid recording credentials or confidential content without controls.
Advisory/security review not completed; no safety badge.
Unknown vulnerabilities and provider data handling are not certified by this public tracking review.

Full authority, access and evidence limits are available in Review context and Access & risk.

Popularity

493 repository stars

Stars observed Oct 9, 2026.

Repository total for TeleAI-UAGI/telemem.

All limitations / Review context

Have MCP write/delete memory operations and external model-provider boundaries changed?

No identified material blocker to an accurately qualified public tracking entry in the limited cited evidence. This is not an installation safety certification; product-specific cautions must remain visible.

Can retain/retrieve agent memories; avoid recording credentials or confidential content without controls.
Advisory/security review not completed; no safety badge.
Local memory store; memory write/delete and bulk-delete tools exist; provider keys/config can enable external model calls.
Reviewed write actions: Write/update memories; Delete or bulk-delete memory records
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
Can store and delete memory; remote model endpoints can receive memory content if configured.
Unknown vulnerabilities and provider data handling are not certified by this public tracking review.
Release evidence proves attributable activity, not entire installation or tool-level safety.
Current Discovery source binding and atomic apply must be generated using MCP100 existing pipeline.
exact authentication contract
first-party data processing and retention
data retention and permission scope
Local-by-default claims depend on configured LLM/embedding endpoints; bulk deletion is destructive.
Radar public tracking editorial review completed in limited scope; not a security or installation certification. Verify setup according to deployment mode and do not invent unresolved facts.

Original activity observations

TeleMem v1.10.0 was released 2026-08-15 with DeepSeek Harness MCP integrations.

Technical identity

github.com/TeleAI-UAGI/telemem

Exact implementation source: https://github.com/TeleAI-UAGI/telemem ↗
Reviewed resource type: MCP Server
Repository identity: TeleAI-UAGI/telemem

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 9, 2026 · Latest source observation Oct 9, 2026

GitHub repository ↗
teleai-uagi/telemem
Recorded repository material and project history.
Includes references whose attribution is not established.

Setup · Watchlist

Install & Agents

Claude Code

Publisher instructions with a documented client setup path.

Source evidence observed Oct 12, 2026.

Additional setup details required — see the specific gaps below.

Install / connect
Publisher instructions
Use the dedicated official docs/MCP.md, not only the TeleMem library README. Install pip install "telemem[mcp]" and register the telemem-mcp stdio command in a supported client; configure TELEMEM_CONFIG and model/provider secrets separately.
pip install "telemem[mcp]"
claude mcp add telemem -e TELEMEM_CONFIG=/absolute/path/to/config/config.yaml -- telemem-mcp
Configure / authenticate
Publisher instructions
The publisher MCP guide documents pip install "telemem[mcp]", console command telemem-mcp (stdio default), Claude Desktop configuration and Claude Code registration. Set TELEMEM_CONFIG to your config YAML and configure the required provider credentials. Do not expose secrets in code or on command lines.
Advanced configuration · claude desktop json
{ "mcpServers": { "telemem": { "args": [], "command": "telemem-mcp", "env": { "OPENAI_API_KEY": "REPLACE_WITH_YOUR_API_KEY", "TELEMEM_CONFIG": "/absolute/path/to/config/config.yaml", "TELEMEM_DEFAULT_USER_ID": "your-handle" } } } }
Check connection
Suggested check
Inspect TeleMem tools in the MCP client after restarting. The official examples/mcp_client.py can exercise memory but writes test state; do not run against real existing memory merely for connectivity. Client registration check: `claude mcp get telemem` (checks registration; inspect tools/read-only calls separately to verify authenticated service access).
Remove / uninstall / revoke
MCP100 setup guide
Stop the application/service using its documented controls. Platform-specific uninstall and credentials management require separate evidence. Client disconnect (claude-code, only if registered using the name `telemem`): `claude mcp remove telemem`. This unregisters the client entry; it does not uninstall packages or revoke remote service credentials.
claude mcp remove telemem
python -m pip uninstall telemem

Official Documentation & Sources

What it does

TeleMem ships a standalone MCP long-term-memory server with eight documented tools.

Capability: Files & Knowledge
Resource type: MCP Server
Best fit: Persistent agent memory and retrieval

Representative uses

add_memory
search_memories
get_memories
get_memory
update_memory
delete_memory
delete_all_memories
memory_history

Limitations

Local-by-default claims depend on configured LLM/embedding endpoints; bulk deletion is destructive.
Radar public tracking editorial review completed in limited scope; not a security or installation certification. Verify setup according to deployment mode and do not invent unresolved facts.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Not documented in the reviewed sources
Permissions: Local memory store; memory write/delete and bulk-delete tools exist; provider keys/config can enable external model calls.
Data handling: Not documented in the reviewed sources
Cost: unknown
Risk and cautions: Can retain/retrieve agent memories; avoid recording credentials or confidential content without controls.

Access scope and cautions

Write actions: Write/update memories Delete or bulk-delete memory records
Risk level: moderate
Security notes: Advisory/security review not completed; no safety badge.

FAQ

Based on reviewed evidence as of 2026-10-09. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: add_memory; search_memories; get_memories; get_memory; update_memory; delete_memory; delete_all_memories; memory_history.

What setup and authentication are documented?

A complete connection procedure is not verified. Recorded transport: stdio. Client notes: List 8 memory tools; optional upstream tests python tests/test_mcp.py. These facts do not supply missing installation commands, credentials or a verified authentication procedure. Authentication: Storage/model backend configuration dependent; not a generic hosted OAuth server.

Can it modify data or perform write operations?

Documented write actions include: Write/update memories; Delete or bulk-delete memory records. Recorded permission boundary: Local memory store; memory write/delete and bulk-delete tools exist; provider keys/config can enable external model calls.

What limitations and risks should I check before use?

Can retain/retrieve agent memories; avoid recording credentials or confidential content without controls. Local-by-default claims depend on configured LLM/embedding endpoints; bulk deletion is destructive. Radar public tracking editorial review completed in limited scope; not a security or installation certification. Verify setup according to deployment mode. Advisory/security review not completed; no safety badge. Can store and delete memory; remote model endpoints can receive memory content if configured. Unknown vulnerabilities and provider data handling are not certified by this public tracking review.