AI Plugin Indexbenchmark alternatives
The most used alternatives to benchmark are memcode, summary, pause. All are knowledge and memory skills with an active GitHub repository, ranked below by GitHub stars and recent activity.
| # | Skill | What it does | Runs | Updated | Stars |
|---|---|---|---|---|---|
| ref | benchmark ThinkfleetAI | 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". | Skill | 1 month ago | 420 |
| 1 | memcode ThinkInAIXYZ | 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. | Skill | yesterday | 6.4k |
| 2 | summary agno-agi | Deliver the Product summary through its configured interface and wiki. | Skill | yesterday | 43k |
| 3 | pause mem0ai | Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments. | Skill | yesterday | 68k |
| 4 | paper-poster wanshuiyin | DEPRECATED — superseded by /paper-poster-html. Kept only as a redirect for muscle memory; do not use for new posters. | Skill | yesterday | 18k |
| 5 | tanstack-ai-memory-mem0 TanStack | 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. | Skill | yesterday | 3.2k |
| 6 | handoff synthetic-sciences | 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. | Skill | 3 days ago | 4.1k |
| 7 | gsd-ns-context open-gsd | codebase intel | map graphify docs learnings mempalace | Skill | yesterday | 11k |
| 8 | edit DAIR-AutoResearch | Add or remove raw sources, or update wiki content, per user request | Skill | 19 days ago | 1.7k |
| 9 | quarter-clone ykdojo | Clone the last quarter of the current conversation, discarding earlier context to reduce token usage while preserving recent work. | Skill | 26 days ago | 10k |
| 10 | shadcn-ui-mcp Jpisnice | shadcn/ui component context and usage from Codex via MCP | Skill | 17 days ago | 3.1k |
| 11 | mcp-setup thejaustin | Spawns and configures Model Context Protocol (MCP) integrations for ShizukuPlus. | Skill | yesterday | 1.5k |
| 12 | screenpipe-meeting-prep screenpipe | Prepare for a specific upcoming meeting using verified identity and prior context. | Skill | yesterday | 22k |
Questions
What is the best alternative to benchmark?
By usage, memcode is the most popular alternative, with 6.4k GitHub stars. The right choice depends on which features and hosting you need.
Is benchmark still maintained?
Its last commit was 1 month ago. You can see current activity on its listing page.