OpenRadar

Tag

#agents

8 open-source projects filed under this tag.

01 Python

aisuite

Andrew Ng's aisuite is a unified Python library for building with multiple LLM providers — one API for OpenAI, Anthropic, Google, Mistral, and more, plus an Agents API with toolkits and MCP support.

#ai#llm#python#agents
14.3k 1.5k Read
02 Go

clawpatrol

Claw Patrol is a Go-based security firewall for AI agents from the Deno team — parse agent traffic at the wire, gate actions with HCL rules before they reach production.

#ai-security#agents#go#firewall
753 31 Read
03 TypeScript

compound-engineering

An opinionated framework for AI-assisted software engineering. Compound engineering treats AI agents as collaborative partners in the development workflow — not just code generators.

#ai#engineering#workflow#agents
3.2k 180 Read
04 Python

mempalace

MemPalace is a local-first AI memory system with 96.6% recall accuracy, MCP server, and knowledge graph — zero API calls required.

#ai-memory#mcp#knowledge-graph#agents
54k 7.1k Read
05 TypeScript

mimo-code

MiMo-Code is Xiaomi's open-source terminal-native AI coding assistant with persistent memory, subagent orchestration, and self-improving features — a serious Claude Code alternative.

#ai-coding#terminal#agents#developer-tools
9.5k 412 Read
06 Python

odysseus

Odysseus is a self-hosted AI workspace with chat, agents, deep research, documents, email, and calendar — your private ChatGPT alternative that runs on your own hardware.

#ai-workspace#self-hosted#agents#privacy
68k 8.5k Read
07 TypeScript

sandbox-runtime

Anthropic's open-source sandbox runtime for AI agents — enforce filesystem and network restrictions at the OS level without containers. Built for Claude Code, works everywhere.

#ai-security#sandboxing#mcp#claude-code
4.4k 317 Read
08 Go

stash

Stash gives AI agents persistent memory across sessions — self-hosted Go binary with Postgres, pgvector, MCP server, and a 9-stage consolidation pipeline.

#ai-memory#mcp-server#postgres#agents
711 35 Read