PocketStrike is a privacy-first mobile AI workstation. It combines zero-cloud native on-device GGUF inference (ARM NEON accelerated) │ with frontier cloud LLMs, multi-step ReAct agent tools, Model Context Protocol (MCP) servers, self-evolving cross-session memory, and FLUX neural image │ generation.
Repository Index
47,133 repositories indexed
73–91 of 91 · Most stars
A token efficient, local LLM friendly agentic coding harness: a complete agent runtime (agent loop, tool pipeline, sandboxing, session persistence) with four front-ends — a Blazor web UI, a headless CLI, and JSON-RPC / ACP stdio servers for editors and automation.
Open-source agentic security operations platform:
Pi.NET 是 Pi 的 .NET 10 移植版。Pi 是一个极简、可扩展的 Agent harness（TypeScript monorepo，约 17.1 万行），本项目把它的核心库逐一移植到 net10.0，让 .NET 生态用上同一套能力。
Source-available semantic and context layer, rule engine, and semantic sidecar for agentic AI and governed analytics. Compiles declarative YAML models into optimized SQL, KPIs, and semantic context across 8 SQL dialects.
Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
Durable execution framework for AI agents in Go. Keeps agent state, tool calls, and execution loops resilient across process crashes.
LLM and agent evaluation for Java & Kotlin. Runs in JUnit and CI. Spring AI, LangChain4j, Koog, Embabel, and any LLM client.
Autonomous multi-agent framework to optimize scientific software
CLI for managing AI agent squads. Status, memory, goals, feedback, and dashboard for your autonomous agents.
Embedded single file SQL database written in Golang
MCP server for spatial transcriptomics analysis through natural language interfaces.
A repo-native coding-agent loop harness for Claude, Codex, Copilot, and other CLI agents. Agents can edit. Gates decide what lands. You set the plan in motion. The agents take a prompt, and each iteration must update specs and commit through guardrails.
Runtime guardrails for Claude Code. Auto-approve what's safe, gate what's risky, block what's dangerous. Dual enforcement, full audit trail. MIT.
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.
Go SDK for Dakera AI agent memory — self-hosted, 88.2% LoCoMo. Vectors, hybrid search, knowledge graphs, sessions.
Run agentic TUIs inside Neovim with persistent float/panel views and editor-context helpers.
Open, audit-grade agentic data quality framework with portable industry packs