Features
Multi-agent shared memory with fleet scoping
Built-in governance with visibility scopes, trust tiers, tenant isolation
Full audit trail on every operation
Knowledge graph with entity and relation extraction
Hybrid recall: semantic + keyword + graph expansion
Self-improving retrieval via per-agent tuning and outcome feedback
LLM enrichment pipeline (classify, entity extract, contradiction check, embed)
Skill Factory distills agent experiences into reusable governed skills
Keystone policies for deterministic enforcement of rules
MCP-native integration for any AI client
OpenClaw plugin for fleet deployments with OTA updates
12 MCP tools: write, recall, list, manage, doc, entity get, tune, insights, evolve, stats, keystones, keystones_set
PII guard with auto-detection and quarantine
Agent cold-start resolution via pre-seeded knowledge and mandatory keystones
SOC 2 compliant and Apache 2.0 open source
Data Agent for data analysis with Python/SQL execution
Plugins Agent integrating 200+ third-party plugins
Web Agent for autonomous web browsing via Chrome extension
Auto plugin selection by the agent
Combined plugin usage for multi-step tasks
Chat-based web UI optimized for swift responses
Open-source full-stack code (backend + frontend)
Local deployment via Docker
Free online demo on OpenAgents website
Data visualization using Python libraries
Integration with 200+ plugins including Klarna, XWeather, Wolfram Alpha
Lemur foundation models for language agents (open-source)
Real-world evaluation and research support
Troubleshooting support via Discord
COLM 2024 publication with paper available
