Compare/claude-mem vs evalmonkey

AI tool comparison

claude-mem vs evalmonkey

Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.

C

Developer Tools

claude-mem

Persistent cross-session memory for Claude Code — auto-capture, compress, and recall

Ship

75%

Panel ship

Community

Free

Entry

claude-mem is a Claude Code plugin that hooks into the agent's full session lifecycle — capturing every tool call, observation, and interaction — compresses them semantically using Claude's agent-sdk, and stores everything in a local SQLite + Chroma vector database. On each new session, it injects only the most contextually relevant history via a 3-layer token-efficient retrieval system. The result: a coding agent that actually remembers your project across disconnected sessions. It's crossed 55K GitHub stars with support for Cursor, Gemini CLI, Windsurf, and OpenClaw. A community audit flagged the unauthenticated HTTP API on port 37777 as a HIGH severity issue — any local process can read every stored observation including API keys. The fix hasn't shipped yet. The 'Endless Mode' beta enables truly continuous sessions with automatic context compression when approaching token limits, making it useful for long-running projects that currently require frequent re-orientation.

E

Developer Tools

evalmonkey

Benchmark your AI agents under chaos — schema errors, latency spikes, 429s

Mixed

50%

Panel ship

Community

Paid

Entry

evalmonkey is an open-source framework for testing how LLM agents degrade under adversarial conditions. You run your agent against 10 standard datasets (GSM8K, ARC, HellaSwag, etc.) pulled automatically from HuggingFace, then apply chaos profiles that introduce realistic failure modes: malformed JSON schemas, artificial latency spikes, 429 rate-limit errors, context-window overflow, and prompt injection payloads. The key output is a degradation delta — evalmonkey shows you exactly how much your agent's accuracy drops under each failure type versus clean inputs. A model that scores 78% on GSM8K normally but drops to 31% when it gets a 429 mid-chain tells you something crucial about its error-recovery behavior that standard benchmarks completely miss. It supports OpenAI, Anthropic (via Bedrock and direct), Azure, GCP, and any Ollama-hosted model. Corbell-AI published this with a clear thesis: agents break in production for infrastructure reasons, not model reasons — and no existing benchmark tests that. evalmonkey was created today (April 17, 2026) and is still at 3 stars, but the core idea is genuinely novel in the evals space.

Decision
claude-mem
evalmonkey
Panel verdict
Ship · 3 ship / 1 skip
Mixed · 2 ship / 2 skip
Community
No community votes yet
No community votes yet
Pricing
Free / Open Source (AGPL-3.0)
Open Source
Best for
Persistent cross-session memory for Claude Code — auto-capture, compress, and recall
Benchmark your AI agents under chaos — schema errors, latency spikes, 429s
Category
Developer Tools
Developer Tools

Reviewer scorecard

Builder
80/100 · ship

This is one of those tools that should have existed from day one of Claude Code. The fact that agents forget everything between sessions is genuinely painful for long-running projects. The 3-layer token retrieval is clever — it filters before fetching. One-command install, multi-IDE support, local-first. The AGPL license is the main friction for commercial teams.

80/100 · ship

Every engineer who's deployed an agent in production knows models fail catastrophically when the API starts rate-limiting mid-chain. evalmonkey is the first tool I've seen that actually lets you reproduce and measure that. The degradation delta report alone is worth the setup time.

Skeptic
45/100 · skip

55K stars and a known unauthenticated API on port 37777 — that's not a footnote, that's a fire. Any process on your machine can read every stored observation and view cleartext API keys. The fix isn't complicated, but it hasn't shipped. Until the port is locked down, this is a hard skip for anyone working on anything sensitive.

45/100 · skip

It's a brand new repo with 3 stars and no documentation beyond the README. The chaos profiles themselves are hardcoded — you can't simulate the specific failure patterns your infra produces. Useful concept, but wait for it to mature before relying on it for production decision-making.

Futurist
80/100 · ship

The real unlock here isn't memory for Claude Code specifically — it's the emerging pattern of agent memory as infrastructure. claude-mem is one of the first tools to implement this at the session-lifecycle level rather than bolting it on as an afterthought. The vector + FTS hybrid approach and 'Endless Mode' beta point at what production agent memory systems will look like in 18 months.

80/100 · ship

Chaos engineering for AI agents is a missing layer in the entire reliability stack. As agents handle higher-stakes tasks, chaos benchmarking will move from 'interesting experiment' to 'required before deployment.' evalmonkey is establishing the vocabulary for that discipline right now.

Creator
80/100 · ship

If you run Claude Code for anything longer than a single afternoon, you know the pain of re-explaining your project on every session start. claude-mem just fixes that. The privacy tags are a nice touch — wrap sensitive info and it won't get stored. The web viewer is genuinely useful for auditing what the agent has learned. Solo devs, this is a clear win despite the security caveat.

45/100 · skip

Too dev-focused for my immediate use, but if I'm running an agent that manages my publishing schedule, knowing it won't break when Anthropic throttles me at 2am is genuinely valuable. I'd want a managed version with a dashboard before adopting this.

Weekly AI Tool Verdicts

Get the next comparison in your inbox

New AI tools ship daily. We compare them before you waste an afternoon.

Bookmarks

Loading bookmarks...

No bookmarks yet

Bookmark tools to save them for later