AI Plugin Index
benchmark
Skill by ThinkfleetAI · updated · ★ 420
Run MemMesh's competitive benchmark harness (LOCOMO / BEAM) to compare retrieval quality, tokens, latency, and cost against Mem0, Zep, full-context, and naive-RAG baselines. Use when the user wants proof MemMesh is better, is evaluating a migration, or asks "how does this compare to mem0". benchmark is published by ThinkfleetAI on GitHub.
Last commit 56 days ago
Apache-2.0: permissive, fine for commercial use
Clear description, installs from GitHub, 420 stars, original repository
Not checked yet. What we check
Install benchmark
Built from the published package, never by AIgit clone --depth 1 https://github.com/ThinkfleetAI/memmesh /tmp/memmesh && mkdir -p ~/.claude/skills && cp -r /tmp/memmesh/integrations/memmesh-plugin/skills/benchmark ~/.claude/skills/benchmarkRun in your terminal. Claude Code loads skills from ~/.claude/skills automatically.
git clone --depth 1 https://github.com/ThinkfleetAI/memmesh /tmp/memmesh && mkdir -p ~/.gemini/antigravity-cli/skills && cp -r /tmp/memmesh/integrations/memmesh-plugin/skills/benchmark ~/.gemini/antigravity-cli/skills/benchmarkAntigravity CLI loads skills from ~/.gemini/antigravity-cli/skills, or .agents/skills for one project.
Skills can run scripts on your machine. Some need an API key: check the README.
Alternatives to benchmark
All alternatives →
Use the enabled Memcode MCP connection to explicitly save approved facts and recall relevant memories across DeepChat conversations. Never save a transcript or retrieve memory automatically.
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
DEPRECATED — superseded by /paper-poster-html. Kept only as a redirect for muscle memory; do not use for new posters.
Deliver the Product summary through its configured interface and wiki.
Use when wiring mem0() from @tanstack/ai-memory/mem0 — a hosted memory adapter that talks to a mem0 server over plain HTTP (no SDK peer). Requires a running mem0 server.
Create a self-contained continuation packet for another agent. Use when the user invokes /handoff, asks to transfer work, or needs the current context saved before another agent continues.
benchmark: common questions
How do I install benchmark?
Run the command above to copy the skill into ~/.claude/skills/. Claude Code picks it up automatically.
Is benchmark free?
The code is published under the Apache-2.0 licence. The service it connects to may have its own pricing.
Is benchmark safe to use?
It scores 68 of 100. Grades: maintenance B, licence A, quality B. The security check has not run for it yet. Review the code before you install. How grades work.
What are alternatives to benchmark?
Similar skills: memcode, pause, paper-poster, summary.