← Browse tools

Specialized agents

Eris

A local-first Rust personal agent using a Markdown vault as memory and grammar-constrained tool calls through llama.cpp, with optional external integrations.

29 stars

Overview

Research summary

Eris is a personal agent organized around a local Markdown vault that remains readable and usable outside the application. It can work with notes, search and retain context, and manage supported personal-assistant tasks through a shared orchestration layer exposed by terminal and local web interfaces. The project uses llama.cpp-compatible local inference and grammar-constrained JSON tool calls rather than requiring a hosted function-calling API.

Its design distinguishes core local behavior from optional network integrations such as messaging or web access. Local-first operation is a deployment property, not a guarantee that a model’s answers are correct or that every enabled integration stays offline. The Rust application is Apache 2.0 licensed.

Model weights, optional services, and the operator’s chosen permissions remain independent of the application code license.

Repository summary

Stars
29
Open issues
Unavailable
Last push
2026-09-15
Commits, 90 days
Unavailable
Repository activity
Not scored
Version
Unavailable

Recorded catalogue figures. View repository data and provenance →

Classification

Pricing & services

Paid services unknown

Whether the provider offers paid products or services has not been established.

Licence scope

Implementation

Recorded implementation details and interfaces for Eris.

Implementation details

Rust agent with Markdown-vault memory and llama.cpp integration

Languages
Rust
Repository type
source

Recorded interfaces and capabilities

Licence scope

Repository

Repository snapshots, release information and recorded maintenance signals.

Repository snapshot

janpauldahlke/eris ↗

Stars
29
Open issues
Unavailable
Last push
2026-09-15
Commits, 90 days
Unavailable
Repository activity
Not scored
Archived
Not recorded

Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).

Maintenance and provenance

Catalogue snapshot
2026-10-06
Stars source
Recorded fallback
Last push source
Recorded fallback

Documentation

Recorded references and research provenance for this entry.

Recorded sources 4

Research metadata

Research date
2026-09-16
Catalogue snapshot
2026-10-06