nyabia-public/nyatibara
6
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
No description
140 commits 1 branch 0 tags 7.9 MiB
  • Rust 100%
Find a file
Exact
Codex 1049d6bd92 docs(architecture): define content-addressed context views
2026-07-17 01:24:19 +09:00
docs docs(architecture): define content-addressed context views 2026-07-17 01:24:19 +09:00
nyati-protocol refactor(runtime): establish canonical model execution authority 2026-07-17 01:01:44 +09:00
nyatibara-agents refactor(runtime): establish canonical model execution authority 2026-07-17 01:01:44 +09:00
nyatibara-auth refactor(runtime): establish canonical model execution authority 2026-07-17 01:01:44 +09:00
nyatibara-core refactor(runtime): establish canonical model execution authority 2026-07-17 01:01:44 +09:00
nyatibara-memory Initial import from nyatif-workspace 2026-05-21 06:36:20 +00:00
nyatibara-providers refactor(runtime): establish canonical model execution authority 2026-07-17 01:01:44 +09:00
nyatibara-tools agents: gate native stores behind native-stores, flip wasm32 build green 2026-06-25 09:37:38 +00:00
.gitignore Initial import from nyatif-workspace 2026-05-21 06:36:20 +00:00
AGENTS.md refactor(agents): own canonical execution end to end 2026-07-16 12:23:49 +09:00
Cargo.lock refactor(runtime): establish canonical model execution authority 2026-07-17 01:01:44 +09:00
Cargo.toml feat(agents): recover stopped session actors 2026-07-15 21:55:32 +09:00
deny.toml Add dependency license policy 2026-05-22 23:36:12 +09:00
README.md Document nyatibara onboarding 2026-05-21 08:54:15 +00:00

README.md

nyatibara

nyatibara is a low-level runtime kit for agentic products.

It is intentionally not a product framework. It owns:

  • provider and auth adapters
  • branch-aware conversation threads and checkpoints
  • memory architecture and storage interfaces
  • compaction/context-engineering primitives
  • minimal tool/runtime event contracts
  • external-event and tool-result ingest helpers
  • generic agent sessions, tasks, artifacts, handoffs, and pending-input primitives
  • dynamic agent registration and runtime spawning

Credential storage is intentionally not part of the core framework contract. Products pass materialized credentials in through env vars, explicit config, or their own secret-management layer.

It intentionally does not own:

  • coding CLI UX
  • team dashboards
  • product-specific session views
  • operator-facing web/TUI layouts
  • user-facing chat transport protocols

Design goals

nyatibara is scoped to support multiple products without pulling product semantics into the core:

  • nyaticode: coding CLI / TUI / web shell
  • nyatipaw: OpenClaw-style assistant integration
  • SNS bot libraries

What is in the workspace

  • nyati-protocol
    • shared provider, event, message, branch, checkpoint, session, task, and memory facet types
  • nyatibara-core
    • branch-aware conversation graph, generic agent runtime, and compaction primitives
  • nyatibara-auth
    • optional Codex-oriented OAuth/token helpers for product layers
  • nyatibara-providers
    • provider routing, capability descriptors, and OpenAI-compatible/Codex adapters
  • nyatibara-memory
    • Mastra-style memory facets with a libsql-first backend

Current boundary

The core model is:

  • conversation tree
  • branch from checkpoint
  • linear replay inside a branch
  • exact history stays recoverable
  • compacted contexts are derived views
  • agent sessions are generic and product-neutral
  • agents can be registered or created dynamically at runtime
  • pending input and task state are first-class
  • external events and tool results can be materialized back into transcript history

The stream split is:

  • nyatibara: domain/provider/runtime events
  • nyatikit: user-facing timeline transport and UI event protocol
  • products: layout, interaction, and product-specific commands

The memory model is:

  • history memory
  • working memory
  • observational memory
  • semantic memory

Why this shape

This project is informed by:

  • LangGraph's durable thread/checkpoint model
  • Mastra's memory layering
  • OpenAI Agents SDK's session/handoff abstractions
  • pi shell's minimal-core philosophy
  • Microsoft Agent Framework's workflow/session split
  • Google ADK's event-first runtime
  • A2A's task/artifact vocabulary

Start with: