Atlas / Skills / rohitg00 / Agentmemory Agents

Agentmemory AgentsSAFE

skills/rohitg00/agentmemory-agents

#1 Persistent memory for AI coding agents based on real-world benchmarks

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
—
Hosts
6 documented
License
Apache-2.0
Stars
29,953
01

Overview

#1 Persistent memory for AI coding agents based on real-world benchmarks

Read from source at commit fa8d5cd2e498OBSERVED · 2026-10-28
Advertisement
02

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
claude-codementioned
codexmentioned
copilotmentioned
cursormentioned
gemini-climentioned
openclawmentioned
03

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: agentmemory-agents
description: How agentmemory wires into host coding agents via the connect command. Use when installing agentmemory into a specific agent, when asked which agents are supported, or when a connect adapter writes the wrong config path.
user-invocable: false
---

`agentmemory connect <agent>` merges the memory server into a host agent's config and preserves any existing servers. REST is the underlying protocol; for MCP-only hosts the adapter wires the stdio MCP bridge.

## Quick start

```bash
agentmemory connect claude-code   # or cursor, codex, gemini-cli, ...
```

After wiring, restart the host or run its MCP reload (for example `/mcp` in Claude Code, or a new session after `devin mcp list` in Devin CLI) so it picks up the server. Then confirm the agent lists agentmemory's tools.

Devin CLI and Devin Desktop can also install the whole plugin with `devin plugins install rohitg00/agentmemory#plugin`, which adds the skills, the MCP server, and the capture hooks in one step. Cloud Devin sessions cannot reach a local agentmemory server, so the plugin is for local sessions only.

For Pi, Oh My Pi, or DeepSeek Harness, start the daemon and choose the matching command:

```bash
agentmemory connect pi --with-mcp
agentmemory connect omp --with-mcp
agentmemory connect dsh --with-hooks
```

Pi and OMP install native recall, capture and bundled skills; `--with-mcp` adds the tools needed by the broader workflows. Reload Pi with `/reload`, or restart OMP, then run `/agentmemory-status`. Restart DSH after enabling its bundled capture plugin. Re-run the matching connector after upgrading or moving AgentMemory so installed runtime paths stay current.

Cursor's connector configures MCP. Install and enable the Cursor plugin through Settings → Plugins → Add marketplace → this repository for lifecycle capture; do not add a second global hook copy.

## Workflow

1. Detect the calling agent. If unknown, ask which host to configure before changing files.
2. Run `agentmemory connect <name>` using a name from the table in REFERENCE.md.
3. Read the command result: an adapter that prints manual setup instructions has not completed installation. Restart the configured host, inspect its actual tool inventory, and perform an authorized save/recall check. A native memory provider and an MCP connection are separate surfaces (see [TROUBLESHOOTING.md](TROUBLESHOOTING.md)).

## Notes

- Hermes, OpenClaw, Pi and OMP connectors bundle skills. For a separate skills installation, use `npx [email protected] add rohitg00/agentmemory --agent hermes-agent --skill '*'` or `--agent openclaw`. Choose the intended host; add `--global` only for a user-wide installation. Avoid duplicate skill installations when a native package already bundles them. Verify skill discovery and read a skill's local support file in that host.
- Native Windows supports `agentmemory connect copilot-cli`. Other automated connectors require macOS, Linux or a host running in the same WSL2 environment; use the host's manual setup instructions otherwise.

## See also

- agentmemory-mcp-tools, agentmemory-rest-api, agentmemory-hooks.

## Reference

The full adapter list with display names and protocol notes lives in REFERENCE.md, generated from `src/cli/connect/`.
04

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.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (1)

INFOPrompt injection · prompt.credential_read · CWE-94, CWE-1427
TROUBLESHOOTING.md:49
and do not read local credential files.
Why it matters. asks the agent to read credentials

Gates applied: no_behavioural_pass.

Audited 2026-10-28 · audit v0.4.1 · source sha fa8d5cd2e498full audit observations/trust-audit/skill/rohitg00__agentmemory-agents.json · Report an issue / request a re-scan
05

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-28fa8d5cd2e498SAFEB89first audit
06

Questions

What does the agentmemory-agents — rohitg00/agentmemory skill do?

#1 Persistent memory for AI coding agents based on real-world benchmarks

Is agentmemory-agents — rohitg00/agentmemory safe to install?

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 skill reads B.

What can agentmemory-agents — rohitg00/agentmemory access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

Which assistants does agentmemory-agents — rohitg00/agentmemory work with?

Its documentation mentions claude-code, codex, copilot, cursor, gemini-cli and openclaw. That is what the text claims, not a compatibility test we ran.

How current is this page?

The grade is for one exact copy of the source (fa8d5cd2e498), read on 2026-10-28. The repository is watched, and a new audit runs when it changes — this is the first audit.

Add this badge to your README

Shows this page's audit result and links back to it. It updates when the audit does.

ModelsAtlas audit badge

Markdown
[![ModelsAtlas audit: Agentmemory Agents](https://modelsatlas.com/skills/rohitg00/agentmemory-agents/badge.svg)](https://modelsatlas.com/skills/rohitg00/agentmemory-agents/)

Not your listing, or something out of date? Claim or update your listing.

Advertisement