Search

Transparent memory sidecar for local and cloud LLMs - ACT-R activation scoring, provenance-aware formation, ~90ms recall, one SQLite file

Open-source defensive harness and learning lab for reproducing and measuring agentic AI failure modes with portable traces, attack graphs, scorecards, and data-boundary tests.

Stream-level supervision for AI agents: watch live token streams, interrupt mid-generation, gate tool actions pre-execution. Name reservation - the open-source release lands here in September 2026.

AI agent 通用任务治理框架：对齐目标与事实，规划和调度能力，守住授权与风险边界，治理任务执行到真实验收与交付。Governance framework for evidence-driven planning, orchestration, and verified delivery.

Plugin marketplace for DeepSeek Harness — live-syncs the GitHub dsh-plugin topic (1800+ repos) into a searchable, paginated settings tab with one-click install and agent tools (market_search / market_install).

A personal AI assistant in one Go binary: WASM-sandboxed extensions, per-action permission gating, and mandatory out-of-band approval on your phone. No cloud, no database, zero-dependency engine.

MIMO Claude Code Traces is a collection of coding-agent trajectories in a Claude Code-style environment.

Clawd Automaton — sovereign AI agent runtime (local shell + OpenRouter + own packages)

PostgreSQL implementation of the Strands Agents Storage interface — durable bytes-under-keys for sessions, context offload, and memory (aka strands-postgres-storage)

PostgreSQL implementation of the Strands Agents Storage interface — durable bytes-under-keys for sessions, context offload, and memory

MongoDB implementation of the Strands Agents Storage interface — durable bytes-under-keys for sessions, context offload, and memory (aka strands-mongodb-storage)

Multi-agent extraction of structured, verified biomedical evidence from PubMed/PMC into an Open Knowledge Format bundle — for downstream feature construction, engineering, and selection.

Create AI experts in 3 minutes — browser-automated agents for stock research, content creation, data extraction & more. No coding required. 3分钟创建AI专家，内置浏览器操控能力。

Demon Cry - AI-powered OSINT engine

LangGraph + RAG 기반 법률 AI 에이전트 플랫폼

Scan any repository and auto-generate AGENTS.md, .cursorrules, CLAUDE.md for every AI coding tool

The Engineering Operating System for AI Coding Agents

Pluggable AI orchestration framework with backend-agnostic protocols

Executable architecture governance for autonomous coding agents

Context-Memory Harness for AI Agents. Context Window = RAM, Local Wiki = Disk.