Hyperon AI Algorithms+AI-DSL+AI-DSL Full

Source Verdict

Per Non-clustered HAA cluster pilot Source 5 close 2026-05-07: [ACTIVE-IDRIS-DSL] / [AI-DSL-DUAL-CITIZEN].

AI-DSL is a service-composition DSL with two distinct technical tracks: (a) an Idris dependent-types layer for typed program/service composition, and (b) a MeTTa combinator/ontology layer in experimental/ai-service-composition/. The MeTTa track gives AI-DSL a HAA-relevant slice; the Idris layer is service-orchestration tooling for the SingularityNET marketplace. The repo is NOT a core cognitive algorithm comparable to PLN / ECAN / MOSES / MeTTa-NARS; treat as marketplace-tooling-with-cognitive-architecture-utility.

Stated Goals (README)

The README frames AI-DSL as providing:

• An expression language for AI service assemblages, with formal mathematical properties (crisp and statistical) — covering algorithmic behaviors, service interactions, and resource usage.
• A toolset for verifying validity of assemblages and automatically composing them — given a precise specification, the AI-DSL toolset should fetch and combine appropriate AI services to deliver the requested function.
• Status (per README): "Up to now the work has been mostly exploratory resulting into prototypes and experimental code covering various aspects of the AI-DSL as opposed to a final product." Two completed phases with technical reports (May 2021, October 2022).

Implementation Surface — Two Tracks

Idris track (typed composition)

77 Idris source files (*.idr) at HEAD aaa702e. File-system tree (git ls-tree) shows the active substrate is in experimental/ai-algorithms/:

• experimental/ai-algorithms/NeuralNets/ — Lib.idr, Lib2.idr, Main.idr, test.idr (neural-network primitives in Idris).
• experimental/ai-algorithms/descent/ — Data/Counter.idr, Data/Matrix.idr, Debug/NoTrace.idr, Examples/LinearRegression.idr, Examples/LogisticLinearRegression.idr, Examples/LogisticRegression.idr (gradient-descent/regression in dependently-typed Idris).

Cross-grep at HEAD: grep -ri 'MeTTa|AtomSpace|PLN|MOSES|Hyperon' --include='*.idr' returns zero hits — the Idris layer does NOT import or define types over PLN/MeTTa/AtomSpace/MOSES atoms. Its center of gravity is service composition with dependent types.

MeTTa track (combinator + ontology)

30+ .metta files in experimental/ai-service-composition/ across two scenario subdirectories:

• english-to-chinese-song/: combinator/ontology experiments named etcs-* — etcs-combinator-data-uncurry-xp.metta, etcs-combinator-sd-data-uncurry-xp.metta, etcs-combinator-sd-data-xp.metta, etcs-combinator-sd-xp.metta, etcs-dtl-atw-ontology-syn-sd-xp.metta, etcs-dtl-atw-ontology-syn-xp.metta, etcs-dtl-atw-ontology-xp.metta, etcs-dtl-ontology-xp.metta, etcs-moderate-ontology-xp.metta, etcs-services.metta, etcs-simple-ontology-xp.metta, etcs-xp.metta.
• recognize-speech-emotion/: combinator experiments named rse-* — rse-combinator-uncurried-xp.metta, rse-combinator-xp.metta, rse-lambda-xp.metta.

This MeTTa track is the AI-DSL slice that connects to the Hyperon runtime — combinator algebra and ontology experiments expressed natively in MeTTa. Recent merge (PR #105 from ngeiswei/combinatory-logic-ai-services, 2025-06-25) confirms ongoing combinator work.

Implementation Surface (canonical)

Repository	HEAD	Date	Verdict
singnet/ai-dsl	aaa702e	2025-06-25	[ACTIVE-IDRIS-DSL] / [AI-DSL-DUAL-CITIZEN] — primary maintained line; Idris 54.4% + Python 33.7% + Shell 9.4% by language; latest merge is ngeiswei combinatory-logic services PR.

Active maintainer: Nil Geisweiller (ngeiswei). Author/responsible per existing wiki +responsible card.

Cluster-Narrative Position

• vs MOSES (HAA Source 5): Adjacent — MOSES evolves programs via genetic search; AI-DSL composes existing services via typed combinators. Different paradigms; no cross-imports at HEAD.
• vs MeTTa-Motto (cross-org sweep candidate): Both touch service composition / LLM agent integration. AI-DSL is Idris-typed + MeTTa combinator; Motto is MeTTa LLM-agent library. Reviewers may flag overlap at the next pilot pass.
• vs PLN, ECAN, AtomSpace, MOSES, NARS, Pattern Mining (HAA + closed clusters): Paradigm-distinct. AI-DSL does not implement reasoning, attention, or learning — it composes services that may include those.
• SingularityNET marketplace coupling: The marketplace/service-orchestration center of gravity makes AI-DSL relevant for cross-org sweeps. The HAA-internal slice is the MeTTa combinator track only.

What This Card Is Not

• Not a core HAA cognitive algorithm. AI-DSL is composition tooling, not a reasoning/attention/learning engine. Position it alongside MeTTa-Motto and the MeTTa runtime, not alongside PLN/ECAN/MOSES/NARS.
• Not a "neural-symbolic bridge." If wiki text claims neural-symbolic-bridge framing, that overstates — the Idris track is purely typed composition; the MeTTa track is combinator/ontology experiments. Neither is a bridge between neural and symbolic representations.
• Not located in src/Composition.idr. The repo has no src/ directory. Idris files live in experimental/ai-algorithms/ as listed above. (V5-rejected pre-cluster-pilot reviewer cite.)
• Not finalized. Per README "Status" section, work is exploratory / prototype-level with completed Phase 1 (May 2021) and Phase 2 (October 2022) technical reports.

Status and Sources

Implementation status: Active, exploratory. Recent commits include combinatory-logic AI services PR (2025-06-25), suggesting ongoing combinator-level work. Two technical reports completed (2021 + 2022) per docs/technical-reports/.

Primary sources:

• Geisweiller, N. et al. AI-DSL Technical Report. docs/technical-reports/2021/ai-dsl-techrep-2021-05_may.pdf. Phase 1.
• Geisweiller, N. et al. (2022). AI-DSL Project Close Report. docs/technical-reports/2022/ai-dsl-project-close-report-2022-oct.md + ai-dsl-techrep-2022-oct.pdf + snet-service-assemblages.pdf. Phase 2.
• Repository README at singnet/ai-dsl.

Cluster-pilot extraction archive: scripts/archive/non_clustered_haa_pilot/source5_NACE_AIDSL_MOSES_MeTTaNARS/ (close 2026-05-07). V5-4 [AI-DSL-DUAL-CITIZEN] carry-forward locked at S5 close.