Releases: akashicmaster/AkashaSeeds
Release list
Akasha Seeds — v1.2 (seeds12)
Akasha Seeds — v1.2.1(seeds12)
A local-first semantic knowledge system for researchers, thinkers, and anyone who wants their notes to do more than sit in a folder.
Two seeds from this release
The seeds series now ships as two variants with identical contents:
| File | Backend | For |
|---|---|---|
akasha_seeds_seeds12.py |
SQLite (default) | General use — the recommended, production-tested build |
akasha_seeds_seeds12n.py |
Silica (native) | Benchmark reference — Akasha's own storage engine, a drop-in twin of the SQLite backend |
Both expand to the same system; only the storage engine differs. Silica matches SQLite on correctness and crash recovery in current tests, with better isolated median latency but weaker concurrent throughput and tail latency. Benchmarks ship in test/benchmark.py.
What's new in v1.2
- MCP service — connect an LLM client directly:
python akasha.py --mcp(stdio) or the portal's/mcpendpoint (HTTP). 15 tools; anonymous callers get a read-only guest session, authenticated tokens unlock scoped writes. - Society — group dialogue spaces. Members speak through their own cast (avatar); spaces can be chat or cowork, with guest and public gates controlled by the creator.
- nebula — a third explorer that surveys your accumulated atoms for dense regions of meaning: candidate concept models that emerged from use, proposed for you to confirm or discard.
- Drop-in concept models — put a concept model file in
lib/akasha/concepts/and its commands appear in the CLI immediately. Fifteen food-domain models (cheese, wine, cocktail, …) ship as working examples; enable their data withonto.pack.enable wine. - Silica — a self-owned native storage engine implementing the AkashaBackend instruction set, groundwork for the hardware path.
- Incremental ontology loading — release updates now load only what changed: re-extracting a seed over an existing install skips unchanged packs entirely, and a new or edited ontology file imports in seconds without touching the rest.
- Process lifecycle hardening — SSH drops, overwrite installs, and crashed daemons self-heal on the next start; no manual process cleanup, ever.
Getting started
Requirements: Python 3.8 or later. macOS, Linux, or Windows.
# 1. Create an empty folder and place akasha_seeds_seeds12.py inside it, then:
python akasha_seeds_seeds12.py # extracts into the current folder
python akasha.py # start (subsequent launches use this command)
On first launch, Akasha loads its built-in ontology and opens an interactive shell. Updating later is the same move: run the new seed in the same folder — your data is preserved, and only changed parts reload.
Verification
- Full test suite: 73/73 evals pass.
- SHA-256:
akasha_seeds_seeds12.py—421c620f893713e48b312d6fa5f783f39966720438b270b78dc71e03d5648244akasha_seeds_seeds12n.py—2f35ab91442f7ac28b11f13a5d668285ace363bc72804c60e0bb4f0e264b62df
Maintenance update — v1.2.1 (2026-08-03)
- Fixed:
def name "description"silently dropped the quoted description;alcould create
dangling aliases that shadowed real atoms. If you useddef/alon v1.2, re-check those
entries — dangling aliases self-heal automatically, but lostdefdescriptions need re-entering. - New opt-in ontology pack:
philosophy(notions, thinkers, repères, authors). - Process lifecycle: every entry path now converges to one healthy daemon + portal — wedged
processes are detected (real-request probes + boot heartbeat), reaped, and respawned
automatically; a slow large-ontology boot is never mistaken for a hang.
Documentation
License
MIT (software and editorial content) · WordNet 3.1 (base ontology — Princeton University) · See LICENSE.md for full attribution and third-party notices.
Akasha Seeds is the independent researcher and humanities distribution. Client limit and bundled content differ across the Seeds, Thesaurus, and Server series.
Akasha Seeds — v1.1
Akasha Seeds — v1.1
A local-first semantic knowledge system for researchers, thinkers, and anyone who wants their notes to do more than sit in a folder.
What is Akasha?
Akasha is a concept-oriented operating system. Instead of organising information into documents or records, it stores atoms — content-addressed chunks of meaning — connected by typed links. The semantic space that emerges between those links is what makes Akasha different from every other note-taking or knowledge tool.
No cloud. No account. Runs locally. Your knowledge stays yours.
What's new in v1.1
- Meaning-layer search —
sim(atoms that mean the same thing),search(free-text semantic search),node.sim(atoms connected the same way),view(one atom's meaning with resonance), andemotion.find. The semantic models learn from your own ontology and graph in the background — no external AI service. - A defined lexicon — namespaces and relation labels now carry proper human- and LLM-readable definitions; recall output shows readable relation names.
- Word-level recall that reaches the ontology —
r <word>surfaces the defining body atoms behind a word, in both directions, with previews. - Unified pagination — long outputs page consistently (
page: 1–10 of N · more). - New Concept Models — Recipe, Formula, and Archives join the ecosystem.
- Roughly 3× larger built-in ontology — humanities, sciences, food systems, history, and a curated lexicon pack, loaded through an ordering-safe two-phase loader.
- A developer verification suite — structural invariants, load tests, a red-team harness, and post-load data verifiers ship in
test/.
Getting started
Requirements: Python 3.10 or later. macOS, Linux, or Windows.
# 1. Create an empty folder and place akasha_seeds_seeds11.py inside it, then:
python akasha_seeds_seeds11.py # extracts into the current folder
python akasha.py # start (subsequent launches use this command)
On first launch, Akasha loads its built-in ontology and opens an interactive shell. No configuration needed.
What you get
- Built-in semantic ontology — concept definitions from WordNet 3.1, emotional vocabulary, geographic coordinates, scientific units, humanities and food-systems knowledge, and more. Every atom you write immediately finds neighbours.
- Concept Models — structured representations of meaningful human activities: Notes, Field Observations, Surveys, Records, Synthesis, World State, Cast, Recipe, Formula, Archives, and more.
- Lens scanner — scan any set of atoms into a structured view, project onto a 4-quadrant scatter plot, aggregate numerically.
- LLM-ready — session-scoped access control, batch
.akfile loading, JCL async job queue. Connect an LLM as a client alongside humans. - Up to 5 simultaneous sessions in the Seeds series.
No mandatory external dependencies
Akasha runs on the Python standard library. Optional features (semantic vector search, NLP trait extraction) install automatically on first launch when TFLite and SpaCy are available. The system runs without them and scales to what the hardware supports.
Documentation
License
MIT (software and editorial content) · WordNet 3.1 (base ontology — Princeton University) · See LICENSE.md for full attribution and third-party notices.
Akasha Seeds is the independent researcher and humanities distribution. Client limit and bundled content differ across the Seeds, Thesaurus, and Server series.