Store and retrieve consensus-validated institutional memory for AI agents with persistent local storage. Ideal for teams building multi-agent systems that need reliable, shared context across conversations.
io.github.l33tdawg/sage
Local install
STDIO
No auth required
How models use it and what it is built for.
Store and retrieve consensus-validated institutional memory for AI agents with persistent local storage. Ideal for teams building multi-agent systems that need reliable, shared context across conversations.
Local install — runs as a subprocess.
Where to find authoritative docs and source for L33tdawg Sage.
Paste any of these into Agent Studio after connecting L33tdawg Sage.
Common questions about connecting and running L33tdawg Sage.
What is consensus validation in Sage?
Consensus validation ensures that institutional memory entries are verified and agreed upon before storage, preventing unreliable or conflicting information from being persisted. The exact validation mechanism is determined by your agent configuration.
Does Sage require external services or cloud infrastructure?
No. Sage runs entirely locally via Docker, storing all institutional memory on your machine. This keeps your agent context private and eliminates external dependencies.
How do I install and run Sage?
Pull and run the Docker image: `docker run ghcr.io/l33tdawg/sage:4.0.0`. It communicates via stdio, so it integrates directly with MCP-compatible clients and agent frameworks.
Can multiple AI agents share the same institutional memory?
Yes. Sage is designed for multi-agent systems, allowing agents to store and retrieve shared, consensus-validated context. This enables teams of agents to build on each other's knowledge.
What happens if agents disagree on a fact—how does consensus work?
Sage validates entries through consensus before persisting them, but the specific consensus rules depend on your agent setup. Refer to the server configuration and agent orchestration layer for details on dispute resolution.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams