github search·zjunlp-lightmem2
zjunlp/LightMem2
zjunlp/LightMem2: As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dynamic memory eviction to minimize token footprints; however, their unconstrained sequence mutations alter layouts, introducing pre...
AgentScore
13.0+0.78
+0.78 vs 24h ago
Adoption8.0
Quality—
Momentum63.3
Community11.6
Quality unrated · weight redistributed
CapabilitiesMemoryMulti Agent
DeploymentLibrary
MaturityExperimental
Score breakdown
Headline plus the four pillars over time. Click any pillar below to see the signals feeding it.
Not enough score history in this window yet — try a wider one.
Pillar contributions
- GitHub stars+3.8%27→ 24.1MCP registry listing0→ 0.0
Pillar = mean of 2 scaled values = 8.0.
Awaiting first reading — these signals apply to this agent and will be ingested on the next tier tick: npm weekly installs, SO questions (7d), Product Hunt upvotes, Docker Hub pulls, Crates.io downloads (90d), Tech-news mentions (30d)
Not applicable — this agent doesn't have the prerequisite (no GitHub repo, no HF mirror, etc.) for these signals to ever apply: HF downloads (30d), PyPI monthly installs
Embed badgeShow your AgentTape rank on your project README
Markdown
[](https://agenttape.com/agents/zjunlp-lightmem2)
HTML
<a href="https://agenttape.com/agents/zjunlp-lightmem2"><img src="https://agenttape.com/api/badge/zjunlp-lightmem2.svg" alt="AgentTape" /></a>
Similar
Vibe-search via embedding cosine
Score envelope last computed 2h ago. Quality is Unrated — agent has no benchmark results yet.