Activity, over time
Daily observations from the public event archive.
Attention
Daily stars & forks
Star accumulation
Cumulative stars
Pull requests
Daily opens & merges
Conversations
Daily issues & comments
Community
Daily accounts & reviews
Releases
Daily releases
Trending history
Daily top 10 · last 90 days · UTC
Mentions
Stars
Forks
Contributors
Latest stargazers
The last 10 distinct accounts we observed this year.
Most active participants
PR, issue, comment & review events in the past year.
Packages
| Package | Version | Downloads · 30d | Trend · 30d |
|---|---|---|---|
| — | — | — | |
| — | — | — | |
| — | — | — | |
semanticav0.7.0 | v0.7.0 | ≥9.8K |
README badges
Embed a badge in your README or website.
Live mentions · last 30 days
Mentions
Semantica is trying to combine GraphRAG, ontology tooling, truth maintenance, provenance, agent memory, MCP retrieval, and SPARQL reasoning in one stack. Ambitious enough that the integration bugs are now more interesting than the feature list. semantica-agi/semantica
有人给 AI 系统底下垫了一层图谱基础设施，敢叫自己“Agent 版开源 Palantir”，Star 已经攒到 11000+，这项目就是 semantica。 它的做法是把企业数据抽成知识图谱：每条事实都挂着来源，每个决策都是能查的对象，为什么做、依据什么、影响了啥，全都能追回去。 GitHub：semantica-agi/semantica 推理这块走的是规则引擎，不靠大模型，结果可复现；碰到互相矛盾的事实会直接标出来，而不是悄悄用新的盖掉旧的。 Neo4j 在内的 8 种图数据库随便换，LangChain、CrewAI 能直接接，还带 MCP 服务，Claude 这类工具也能连上用。 金融、医疗这些行业比较对口，普通项目拿它当 Agent 的长期记忆也够用，一条命令就装上。