- Rust 98.7%
- C++ 0.9%
- Python 0.4%
| Filename | Latest commit message | Latest commit date |
|---|---|---|
The harness judges candidate persona states before any Mind holds them, through the same `project` the live turn will use: every case is one `project` call. - `--room <fixture.toml>`: a mocked room in place of the mouth and the room tail: her id, rooms, messages (sender, display name, room, ago, body; new, tag, mentions, dm, follow_up, reply_to), a mocked now and a "last heard from" table. The fixture is a MouthReader, so addressing is still `address::is_for`. The live room filter that `--room` used to name is now `--in`. - `--state` is checked as a put checks content: huginn-mind's P1 to P3 now live in one owner, `persona::validate_document`, which the put calls. - `--through persona`: the Persona stage (C3b's first piece). One tool-less connector call under Ghostlight's persona membrane over identity, narration and the heard lines; prose capped at 180 words; would-say lines are the double-quoted spans; usage per call. Tuning gains `[persona]` (model, guidance, words). - `--batch <plan> --out <md>`: states x scenarios x samples, one Markdown report with packets, narration, prose, would-say lines, word counts, distinct-2 and cross-state word similarity, and a total-usage footer. - `--simulate <plan> --out <md>`: up to eight personas taking turns in one room. Wake is is_for plus the ruled set (addressed, any human in her rooms, the beat); `wake = "all_messages"` is the old loop as a control. Woken personas run in a seeded order; quoted lines join the room as from her id. State does not evolve (`state_after_turn` is the seam for C3b/C3c). Metrics: messages, silence, who addresses whom, Mind-to-Mind chains, lexical convergence, a work-talk heuristic, usage. - With a state file and a fixture no daemon and no mouth is needed (bin test). - Request ids take the wall clock, so a fixture's fixed now cannot replay. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> |
||
| .voidbot | ||
| crates | ||
| docs | ||
| schemas | ||
| .gitignore | ||
| AGENTS.md | ||
| Cargo.lock | ||
| Cargo.toml | ||
| LICENSE | ||
| README.md | ||
| rust-toolchain.toml | ||
Huginn
Huginn is the GameCult memory organ. It owns each agent instance's mind as typed state: what an instance remembers, which of that memory is admitted to steer its next action, and the provenance of every admitted claim.
Upstream: https://github.com/GameCult/Huginn.git
Status. Live: huginn-mind (admission with receipts, typed queries, derived status), huginn-daemon (CultNet RUDP with a Qdrant semantic index), and the huginn CLI from crates/eureka-state (whoami, view, query, admit, schema). The eureka instance runs on Yggdrasil. Entry points: cargo check --workspace, crates/huginn-mind/src/admission.rs, crates/huginn-daemon/src/serve.rs, schemas/cultnet/. Planned: what each crate does next is owned by the eureka-body cut specs in the mind and docs/eureka-body-map.md; the legacy .voidbot/ Persona migration belongs to the portable-Persona work.
Authority
- An instance owns its mind; Huginn owns the state. Huginn is the single writer of an instance's memory documents. No other service, script, or agent writes them.
- Memory documents are CultCache state.
huginn-mindpersists them through CultLib's Rust CultCache into a redb store at<state_root>/minds/<instance>/mind.redb.huginn-daemonserves one such mind over CultNet RUDP: admission and the read side ridecultnet.operation_request.v0andcultnet.operation_response.v0, and the two wire schemas answer a schema catalog request. - Retrieval depends on Qdrant directly, with no second store and no second
writer.
huginn-daemonkeeps one collection per mind,huginn_mind_<instance>, as a projection of the mind: one worker thread embeds each indexable document through Ollama and writes its point, off the serving path, and a restart compares the mind with the collection and writes what is missing. An unreachable Qdrant or Ollama shows inwhoamias the index's status and is retried; admission never waits on it. The daemon requires--qdrant-url,--ollama-urland--embedding-model;--ollama-urlrepeats for each GPU host and--reserve-ollama-urlfor each CPU host, and the GPU hosts embed together while the CPU hosts serve only when none can. Aquerycarryingsemanticis answered through the same selection as any other: the index supplies candidate ids and scores, and the mind keeps only the documents it holds and the selection admits (ask forin_forceto exclude resolved ones), ordered by score. It takes no cursor, and it is refusedUnavailablewhile the index is failing or refused. - Mind state is not version-controlled. It lives in Huginn's store, not in any repository.
Generic .cc inspection is not Huginn's job. CultCache Studio inspects and
edits .cc state. Huginn reads and writes minds.
Layout
A Cargo workspace of five crates (crates/eureka-pipeline holds the document shapes and keys, crates/mind-body the control store, unit launcher, mind-heartbeat, the inert mind-persona organ and the mind-self-run actuator; the three below are the mind, the daemon and the client):
crates/huginn-mind: storage, identity, admission, and queries and derived status over memory documents.crates/huginn-daemon: the CultNet surface. The socket, the sessions and the process, and no rule. The operation envelope both sides speak ishuginn-mind's.crates/eureka-state: the client core,HuginnClient::call: one request to a daemon over CultNet RUDP, a deferred answer resolved, and no state. Itshuginnbinary is the agents' CLI: whoami, view, query and named recipes, admit with read-back, schema.
huginn-mind is live: it opens one instance's store (an owned redb CultCache
at <state_root>/minds/<instance>/mind.redb, locked for the mind's lifetime),
and refuses a store whose instance document names another instance, whose
epoch record is foreign, or whose types are not a mind's. It admits batches
of pipeline documents through one commit path: the leaf's bounds, formats and
keys, then the organ's cross-document rules (references, in-force status,
the resolution matrix, derived resolutions and stewardships), then one
compare-and-swap that lands the batch whole with a receipt naming the exact
bytes it read and wrote. An exact replay answers with the stored receipt.
It reads them back the same way: a document with the facts of its admission
joined from that receipt and its status derived at read time, and typed
queries over one mind. Status is never stored, and the views derive it
through the same rules admission does. Document shape and keys come from
eureka-pipeline (crates/eureka-pipeline); the store is CultLib's Rust CultCache.
huginn-daemon opens one mind, binds one UDP socket in that order, and
answers every frame on the session it arrived on: one operation per Mind
method plus whoami, whose payload is the mind's own types as named
MessagePack. A refusal is an answer with a rejected status, never a
transport error; an envelope that does not decode is answered with a typed
failure and reaches no mind. The two schemas it publishes live in
schemas/cultnet/, listed in its index.json, and are pinned to their
derivation by a test.
The campaign's cut specs in the mind (eureka-body) and
docs/eureka-body-map.md own what each crate does next.
cargo check --workspace
cargo run -p huginn-daemon -- --state-root <abs> --instance <slug> --bind 127.0.0.1:17872 `
--qdrant-url http://127.0.0.1:6333 --ollama-url http://10.77.0.4:11434 --embedding-model qwen3-embedding:0.6b
The deployed daemon (instance eureka on Yggdrasil) is installed and run by
gamecult-ops/runbooks/huginn-yggdrasil.md.
Persona
Huginn's legacy repo Persona lives under .voidbot/. Its state/huginn.cc
holds legacy void.* documents and its voice/identity.json names the
Persona. The two disagree about jurisdiction; that migration belongs to the
portable-Persona work, not to this workspace, and nothing here reads or writes
.voidbot/.