Self-hosted AI tutor and learning assistant for self-study, e-learning, and exam prep. Turn study notes, PDFs, and lecture notes into a chapter learning path and a quiz. It only teaches a sentence it can quote. Bring your own model key.
DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with independent solvers, scorer and runners.
- benchmark
- calibration
- decision-making
- evaluation
[ICML 2026] Let LLMs invent and evolve languages for efficient reasoning.
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
The repository host gives no description.
Wrap Gemini CLI as an OpenAI-compatible API service, allowing you to enjoy the free Gemini Pro model through API!
Investor’s Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?
面向企业售后场景的 Python Agent 全栈演示:FastAPI、SQLite、LangChain RAG、LangGraph、Vue 与 Docker,含租户边界、评估和故障验证。
BIA Bob is a Jupyter+LLM-based assistant for interacting with image data and for working on Bio-image Analysis tasks.
JevStyle: local decision models for AI agents. Classify, route and score with a probability per option. systemone-compatible local server, MCP tools, Claude Code guard. Open weights, Apache-2.0.
VisSearch-Bench is a benchmark of 204 human-written tasks that test how well multimodal agents find, organize, and use visual evidence across multiple steps of web search.
Public code release for the paper "The Surprising Effectiveness of Deleting Weights in LLM Post-Training"
面向研发团队的 CI 失败检索与证据化诊断工作台。FastAPI + LangGraph + Qdrant + Vue,支持 JUnit 接入、历史溯源与诊断缓存。
ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.
DeepSeek Harness Desktop 插件,让 AI Agent 用自然语言构建、检查和维护可编辑的 SideFX Houdini 工程,支持程序化建模、HDA、场景诊断与渲染。 | A DeepSeek Harness Desktop plugin that lets AI agents build, inspect, and maintain editable SideFX Houdini projects with natural language, including procedural modeling, HDAs, scene diagnostics, and rendering.
Run Qwen3.8-27B locally on Windows with one NVIDIA RTX GPU: chat and an OpenAI-compatible API. On an RTX 5090 the fastest model averaged 2,298 tok/s on our own JSONL edit task (one request at a time, thinking off, v0.1.4).
The repository host gives no description.
Smart routing, seamless flow
三个可运行的 AI 工程项目:可追溯 RAG、提示词评测与受守护的 NL2SQL 分析
Fault-injected tool environments with side-effect grading for evaluating and post-training LLM agents
Translated大师,我悟了 (Dashi, Wo Wu Le, "Master, I've Got It") | A multi-turn heuristic teaching agent
[ACL 2025] The official implementation of the paper "PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free".
PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.
Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.