Search

An intelligent RAG-based system for extracting and answering questions from documents using semantic search and LLMs.

Detect LLM confabulation with semantic entropy (Farquhar et al., Nature 2024) and gate agent actions on it.

MongoDB session manager (storage backend) for Strands Agents — persists sessions, agent state, and messages

cara — a local-first, completeness-gated code-review engine an AI agent drives; the LLM stays outside the trust boundary.

A Vite+ oriented, AI Agent friendly front-end toolchain

YoloRadar CLI — local knowledge-graph planning (sync, plan, buy) for the AI agent marketplace

Read active VS Code editor context and diagnostics from Pi

Backstage Local Provisioner Agent - Provisions local development resources

Cut LLM context token costs: MusCoRe colour-frequency serialisation for structured state. Verified reduction vs JSON, on-chain sealed protocol (cert df9822d8).

A lightweight node-flow runtime for building tool-using agents. Import name: agent_core.

Cadence sync for teams agent-coding in the same room — one dashboard that says when to PROMPT and when to TALK.

FlowJet (fj) — one-shot CLI coding agent powered by soothe-nano

A wrapper around an ML coding CLI: enter at a job, get a named resumable session, optionally driven by a workflow.

Python-only autonomous runtime that watches/analyzes errors with safe local auto-fix fallbacks.

A code-native agentic framework for embedding robust agentic runtime into software components.

SQL session manager (storage backend) for Strands Agents via SQLAlchemy — one provider for SQLite, PostgreSQL, MySQL, and more

Production-grade, non-breaking live debugger and telemetry agent for Python.

A minimal visual harness for agentic coding.

CrewClaw is the digital worker for your workspace

Provider-neutral bounded agent runtime for Android/JVM: controlled context (trust/priority/budgets), profile-scoped tools, OpenAI-compatible live mode, governed-evolution eval, and a high-risk-pause device loop.