peon-mem
by VineetV2
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PEON_AI_MODE | No | AI mode: gated or off (off disables all LLM calls). | gated |
| PEON_DISABLED | No | If set to any value, disables Peon entirely (for A/B testing). | |
| PEON_DAEMON_URL | No | URL of the Peon daemon. | http://127.0.0.1:3737 |
| PEON_MEMORY_DIR | No | Name of the per-project brain directory. | .peon |
| PEON_OLLAMA_URL | No | URL for local Ollama embedding server. | http://127.0.0.1:11434 |
| OPENROUTER_API_KEY | No | API key for consolidation and embeddings (OpenRouter recommended). Without this, Peon works lexical-only. | |
| PEON_EMBEDDING_MODE | No | Embedding mode: api, ollama, local, or off. | auto |
| PEON_EMBEDDING_MODEL | No | Embedding model name, e.g., openai/text-embedding-3-small or an Ollama model. | |
| PEON_FLUSH_MIN_CHARS | No | Consolidation cost gate: minimum characters before triggering consolidation. | 6000 |
| PEON_PROCESSING_MODEL | No | Model used for consolidation. | google/gemini-2.5-flash-lite |
| PEON_CONSOLIDATION_MAX_DELTA_CHARS | No | Maximum chunk size for consolidation to prevent truncation stalls. | 60000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/VineetV2/peon-mem'
If you have feedback or need assistance with the MCP directory API, please join our Discord server