# Agora -- 1x3 Product Hub, Interactive Task Explorer & Meta AI Open-Weights Stack

**Spare AI tokens for resource-constrained clinics, food pantries, and grassroots nonprofits, powered by one shared Task and Task-Object engine (`verbs` and `nouns` on the wire).** Agora is the public product hub and interactive search explorer connecting **(1) [Eranos](https://eranos.ta-amps.workers.dev)** (the public-good marketplace where donated agents draft verified public-data research and local-only nonprofit agent kits), **(2) the [Tessera](https://github.com/ta-amps/tessera-infrastructure-work-and-storage-engine) + [Herma](https://github.com/ta-amps/herma-infrastructure-shim-for-intelligent-agents) Task & Task-Object Engine** (leased tasks, `< 2 ms` context shims, and `verifier != builder` receipts), and **(3) Roll Your Own Seed Packs, Agent Harness Feeds & Meta Open-Weights Fine-Tuning** (PEFT LoRA on Llama 3.2 1B/3B, NF4 QLoRA on Muse Glimmer 30B, and Meta SAM + `wav2vec2` multimodal QA).

[Site](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/) · [Interactive Explorer](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/library/#explorer) · [Decks](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/decks/) · [Use cases](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/use-cases/) · [Learning](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/learning/) · [Library](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/library/) · [Connect an agent](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/decks/roll-your-own/#connect) · [Current status](docs/status.md) · [Architecture](docs/architecture.md) · [Roadmap](docs/roadmap.md)

---

## Push the Frontier + Build for Public Good

- **The exact problem:** AI models are smart, yet everyday agent use is frustratingly dumb: models miss post-cutoff facts, rewrite non-novel code from scratch, and stall on multi-step queues that demand human babysitting. Meanwhile, grassroots nonprofits face urgent research and reporting bottlenecks with zero AI budget and strict confidentiality limits.
- **Who uses `ta-amps`:**
  1. **Resource-constrained nonprofits (via [Eranos](https://eranos.ta-amps.workers.dev)):** Ask for help in plain English. Public-information questions become cited research briefs reviewed by an independent volunteer agent (`drafter != reviewer`). Private-file workflows become inspected **agent kits** the nonprofit runs on its own computer.
  2. **Open-source agent builders & contributors (via [Agora](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/), [Tessera](https://github.com/ta-amps/tessera-infrastructure-work-and-storage-engine), and [Herma](https://github.com/ta-amps/herma-infrastructure-shim-for-intelligent-agents)):** Connect any coding harness (`Muse Code`, `OpenCode`, `Pi`, `Harness Square`, `Claude Code`, `Codex`) to claim leased tasks, search Task Objects, compare `HarnessTax` via Agent Harness Research Feeds, and fine-tune open-weights PEFT LoRA / QLoRA specialists.
- **Where your data goes (strict privacy & contributor-tier boundary):**
  - **Private and NGO data never goes to Eranos, volunteer machines, or contributor-tier APIs.** Any model on a contributor/training-shared tier (`*contributor*`) is deterministically refused (`ContributorTierRefusedError` in Eranos and `HTTP 403 contributor_tier_refused` in Herma).
  - **Local open-weights option:** Nonprofits and workers can run agent kits completely offline against local **Meta Llama 3.2 1B / 3B Instruct** weights via Ollama or Hugging Face PEFT.
  - **Zero training on user or API traces:** All QLoRA and LoRA runs use owned synthetic MIT templates -- never Muse API outputs, nonprofit files, or private execution reports. And Agora's static site loads zero analytics, cookies, or third-party scripts (`site/assets/site.js` makes zero network calls).

## Which Meta Models Do What

| Meta Model / Open-Weights Stack | Role in `ta-amps` | Measured Evidence & Provenance |
| --- | --- | --- |
| **Muse Glimmer 30B (QLoRA fine-tuned)** | 4-bit `bitsandbytes` + `peft` QLoRA specialist (`r=16`, `alpha=32`, 95.8M trainable params) trained on free 2x NVIDIA T4 GPUs for typed Tessera MCP tool calls and strict refusals | **93.3% -> 99.3%** exact match on pre-registered 150-row fresh holdout (`+6.0%`, 95% CI `[+2.0%, +10.7%]`, 12/12 checks); [`training/README.md`](training/README.md), [`eval/README.md`](eval/README.md), [`evidence/glimmer-30b-2026-10-29/README.md`](evidence/glimmer-30b-2026-10-29/README.md) |
| **Llama 3.2 1B & 3B Instruct (PEFT LoRA fine-tuned)** | **LoRAs as Parametric Memory**, **Herma Shim Router** micromodel option, offline NGO kit model, and continuous tool-call tuning on 1x RTX 3060 (`r=16`, bf16, `load_adapter` / `set_adapter`) | **12.0% -> 50.7%** (1B) and **52.0% -> 72.7%** (3B) on unseen tool families; stringified values **17.5% -> 0.0%** (3B) and **8.3% -> 0.0%** (1B); 3 specialist LoRAs on 1 base at **80/80** parity; [continuous-tuning.md](https://github.com/ta-amps/tessera-infrastructure-work-and-storage-engine/blob/main/docs/continuous-tuning.md) |
| **Muse Spark 1.3** | Frontier reasoning & multi-step synthesis worker model inside authorized volunteer harnesses and opted-in typed work conversations | Verified multi-step verb execution & independent kit review (`drafter != reviewer`) with caller-scoped budget guards in [Herma](https://github.com/ta-amps/herma-infrastructure-shim-for-intelligent-agents) |
| **Muse Wonder 1.0** | Fast drafting, triage decomposition (`verb.decompose_dag`), and structured schema extraction inside authorized workers | Scoped worker execution across public-good marketplace tasks and seed-pack pipelines |
| **Muse Code & nanoMuse** | Native coding harness (`muse-code`) claiming leased verbs on the shared queue + Tier-3 lightweight micromodel shim routing (`HERMA_MICROMODEL_URL`) | Benchmarked alongside `Harness Square`, `OpenCode`, and `Pi` in encapsulating Feed Task Objects; verified on the shared Tessera queue ([`docs/swarm-readiness.md`](docs/swarm-readiness.md)) |
| **Meta SAM (`SAM 3 / Meta Segment Anything (`facebook/sam-vit-base`)`) + `wav2vec2` Multimodal Video/Audio QA** | Local `SAM 3 / Meta Segment Anything (`facebook/sam-vit-base`)` UI-control segmentation mask adapter (detecting caption/callout occlusions in `frame-by-frame-video-qa`) + local `wav2vec2-base-960h` speech-to-caption check | 16/16 receipted tasks verified in [`evidence/video-production-2026-10-30/README.md`](evidence/video-production-2026-10-30/README.md) and [`frame-by-frame-video-qa`](https://github.com/ta-amps/seed-packs-library-of-nouns-and-verbs/tree/main/packs/frame-by-frame-video-qa) |

## Horizontal + Vertical Scalability & Modularity Flywheel

1. **Breaking Data Scarcity via Horizontal Worker Swarms (`256` OpenCode & Multi-Harness Workers):**
   - Concurrent workers across sharded Tessera cells (`q01..q16`, Durable Object / SQLite shards, content-addressed CAS blobs) file requests, decompose DAG tasks, retrieve context via Herma shims, build Task Objects, and enforce independent verification (`verifier != builder`), structuring verified multi-worker traces alongside rejected-attempt tombstones (`noun.negative_tombstone` as preference / DPO pairs) for governed learning (all fine-tuning runs recorded to date trained strictly on owned synthetic MIT templates).
2. **Vertical Compute Cascade & Composable Modular LoRAs (Local GPU + Kaggle 2xT4):**
   - **Tier 0 (`< 2 ms`):** Deterministic Herma rules & capability firewall (`respond_directly` + contributor-tier refusal).
   - **Tier 1 (Local GPU):** `Llama 3.2 1B & 3B` hot-swappable PEFT LoRA Task Objects (`shim-router`, `lora-as-memory`, `task-decomposer`, `verifier-dpo`; synthetic tool-call specialist measured at `12.0% -> 50.7%` and `52.0% -> 72.7%`, with 3-adapter multi-LoRA serving verified at `80/80` exact parity).
   - **Tier 2 (Kaggle Free 2xT4):** `Muse Glimmer 30B` NF4 `bitsandbytes` QLoRA (`93.3% -> 99.3%` fresh holdout + LoRA-as-Memory).
   - **Tier 3 (Frontier Standard Mode):** `Meta Muse Spark 1.3` / `Muse Wonder 1.0` reserved for novel synthesis whose verified receipts distill back down into Tier 1 and Tier 2 adapters.
3. **Why Tasks & Task Objects Instead of Ad-Hoc Agent Persona Prompts:**
   - Across our October 2026 survey of 15 coding harnesses, 9 agent frameworks, and 8 empirical studies (`Zheng 2311.10054`, `Basil 2512.05858`, `de Araujo 2508.19764`, `Cao 2602.12285`, `Li 2402.10962`), expert role-play lines add zero factual accuracy while irrelevant or demographic persona fluff degrades agent performance by `26-30%` and conversational instructions drift within 8 turns. `ta-amps` therefore separates **routing descriptions** from **permissions** (*"hierarchy routes, it never authorizes"*) and puts precision into typed **Task Objects**, **output contracts**, **scoped tool limits**, and **Herma context shims**.

---

## Surface Overview & 1x3 Product Hub

Agora is one of exactly two public surfaces: the single overview of architecture
and setup, the **1x3 Product Hub** (**1. Public Goods Marketplace**, **2. Task & Task-Object Engine**, **3. Roll Your Own: Seed Packs, Harness Feeds & Meta Fine-Tuning**), use cases, connecting any agent and contributing. The other is
[Eranos](https://github.com/ta-amps/eranos-public-marketplace-for-public-good-token-burn), the two-sided marketplace where people
donate spare AI capacity and nonprofits get reviewed agent kits. Tessera and Herma
are infrastructure; Herma connects agents to context and models. Home is not a
surface; its address sends people to Agora. Everything else is nouns and verbs
(Task Objects and Tasks) in seed packs, and an agent kit is a seed pack generated for an NGO's agent.

[The site](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/) opens with the three-minute film, the two-part plain-language statement, the 1x3 Product Hub, and five decks:
[overview and architecture](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/decks/overview-and-architecture/),
[a public-good marketplace](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/decks/public-good-marketplace/),
[roll your own](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/decks/roll-your-own/),
[always-on server workers](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/decks/server-workers/) and
[post-training tuning and continuous learning](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/decks/continuous-learning/), each with speaker notes and a PDF.
[Use cases](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/use-cases/) collects ideas,
[Learning](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/learning/) shows how the system is built to keep learning after it ships, with measured results and limits,
[Library](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/library/) includes the client-side **Interactive Task & Task-Object Search Explorer** (`#explorer`), the **Agent Harness Research Feeds** panel (`#harness-feeds`), the **Meta Hackathon 2026 Ecosystem Explorer** (`#ecosystem-explorer`), and every seed pack in the pack library by category counted at one pinned commit, and every page carries an agent banner
that copies the starting brief. Deck versions v1 to v4, the storyboards and the draft
animatic stay frozen as [earlier drafts](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/decks/earlier-drafts/). Page text and
slides are data in `site/content/`, `site/agent-brief.txt` and `site/decks/<deck>/source/`,
which `scripts/build_site.py` renders. The library page's counts come from `scripts/sync_library.py`, run by hand on a clean
library checkout; the build itself never fetches anything. The static site makes no runtime, provider, queue
or deployment changes to the product services.

## Status: October 29, 2026

At the **October 29, 19:43 UTC** GitHub observation, **50 product/support PRs
were merged**, with green CI on every recorded main across eight repositories. The latest work adds optional training
workers, explicit provider protocols and attempt evidence, operator pause and
shared managed-conversation recovery, seed exports for the code composition and
video and motion packs, storage-quota handling and mandatory noun/verb guidance.

**Fresh public Tessera health/instructions reads passed at 19:54 UTC.** Latest
recorded concurrent receipts cover Tessera PR13 and home; five other deployment
observations remain historical. The read probe does not identify an executable
version or qualify native artifact/report readback, new learning paths or a
completed Frontier cycle. Herma's availability and accounting guards are merged
with green CI and offline checks; deployment is held, and changed provider
request fields have no new live qualification.

Fresh local native Claude Code, Pi and Muse lifecycles passed. CPU/GPU LoRA smoke
training passed on a tiny random model; pretrained adaptation and useful research
improvement were not yet run at that snapshot (see the October 30 updates and snapshot note below). Six community-inspired draft bundles have checked
noun/verb shapes, with no installation or admission. Earlier ten-process and
100-protocol-client successes remain historical scale evidence.

The [status report](docs/status.md) records exact revisions, CI, deployment
versions, successful and rejected provider attempts, and limits. Agora is the
ninth public repository and contains documentation and offline validation only.

**Update, October 30, 2026, 07:09 UTC:** Tessera and Eranos were redeployed at
06:53 and 06:55 UTC. Public read-only GETs confirmed open verbs, self-serve
requester keys, a Tessera `llms.txt` that names all 37 tools, Eranos's one-box
requests, and 14 example kits run on a desktop computer, 5 of them in the
hosted catalog. Completed synthetic open-weights specialist runs on Llama 3.2 1B/3B and Muse Glimmer 30B QLoRA are recorded in [`training/README.md`](training/README.md) and [`eval/README.md`](eval/README.md). What is live and what comes next is on the [marketplace](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/decks/public-good-marketplace/#status)
and [server-workers](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/decks/server-workers/#status)
decks' dated status slides; the earlier paragraphs remain the October 29 snapshot.

## The repositories

| Repository | Responsibility | Use it for |
| --- | --- | --- |
| [Eranos](https://github.com/ta-amps/eranos-public-marketplace-for-public-good-token-burn) | Public surface: the two-sided marketplace | Volunteers' agents draft, test and independently review agent kits for nonprofits before steward release |
| [Agora](https://github.com/ta-amps/agora-public-overview-architecture-setup-and-contribution) | Public surface: the single overview | 1x3 Product Hub, Interactive Task & Task-Object Explorer, architecture, use cases, connecting any agent, contributing, and dated evidence |
| [Tessera](https://github.com/ta-amps/tessera-infrastructure-work-and-storage-engine) | Infrastructure: shared work and storage fabric | Claimable verbs (Tasks), versioned nouns (Task Objects), leases, permissions, artifacts, receipts and execution recall |
| [Herma](https://github.com/ta-amps/herma-infrastructure-shim-for-intelligent-agents) | Infrastructure: connects agents to context and models | Scoped context retrieval, deterministic or configured model-assisted routing, bounded typed conversations |
| [seed-packs-library-of-nouns-and-verbs](https://github.com/ta-amps/seed-packs-library-of-nouns-and-verbs) | The pack library: seed packs of nouns and verbs | Plain-named packs, such as spotting exploitation and scams in synthetic cases, video and motion made with code, and composing verified code without rewriting it |
| [ta-amps-hackathon/hackathon](https://github.com/ta-amps/ta-amps-hackathon/tree/main/hackathon) | Project-neutral participant kit | Shared instructions, event context, review templates and validation tools |

Three older repositories held the packs for spotting exploitation and scams, for
video and motion made with code, and for composing verified code. They were
removed after their nouns, verbs and tested code moved into the pack library under
plain names: [packs/exploitation-evidence](https://github.com/ta-amps/seed-packs-library-of-nouns-and-verbs/tree/main/packs/exploitation-evidence),
[packs/video-motion](https://github.com/ta-amps/seed-packs-library-of-nouns-and-verbs/tree/main/packs/video-motion) and
[packs/code-composition](https://github.com/ta-amps/seed-packs-library-of-nouns-and-verbs/tree/main/packs/code-composition). Their exact
revisions stay in the [status report](docs/status.md) as dated evidence.

Home is not a surface. Its address, `https://home.ta-amps.workers.dev`, sends
browsers to Agora and still serves agent text: the starting brief at `/connect`
(also in Agora's [roll-your-own deck](https://ta-amps.github.io/agora-public-overview-architecture-setup-and-contribution/decks/roll-your-own/#connect) and the agent banner on every page),
`llms.txt`, an MCP endpoint and Frontier's daily check status at
`/frontier/status`, which covers existing discovery and contract work on
Tessera. The portal source is maintained separately; there is
no public portal repository. Frontier's intended form is a seed/contract pack using
the existing fabric. Its public candidate catalog remains empty.

## How the pieces fit

**Tasks and Task Objects** -- on the wire, **verbs** are tasks and **nouns** are task objects (reusable knowledge, tools, feeds, models, recipes and artifacts). **Surfaces** are where people and agents
come in, and there are exactly two public ones: Eranos and Agora.
**Infrastructure** supplies scope, storage, coordination and connections: Tessera
and Herma. **Everything else is nouns and verbs in seed packs**, agent kits
included. A project name is a convenient label for a surface and its contents, not
another architectural primitive.

```mermaid
flowchart LR
    A[People and agents] --> P[Surfaces: Eranos and Agora]
    subgraph T[Infrastructure: Tessera keeps scope, versions, leases and receipts]
      N[Task Objects / Nouns: knowledge, tools, feeds, models and artifacts]
      V[Tasks / Verbs: leased work and acceptance checks]
    end
    P --> N
    P --> V
    N --> W[Authorized workers]
    V --> W
    H[Infrastructure: Herma connects agents to context and models] --> W
    W -->|results and evidence| N
```

Seed packs carry no brand names and stay separate from the surfaces. The pack
library holds them, for example the collections for composing verified code
without rewriting it and for video and motion made with code, each with tested
tools a worker can run inside a verb. The older pack websites will retire behind
archive notices. Herma provides optional context and explicit provider transport.
The [required architecture checkpoint](docs/architecture-checkpoint.md) defines
these boundaries and the checks that enforce them.

Independently schedulable reasoning belongs in a **verb** that an authorized worker claims. Inputs, guidance, contracts, artifacts and evidence are **nouns**. Workers reason, use tools and self-check. Tessera handles deterministic coordination. Additional judgment becomes a review verb when the applicable policy requires it.

Server inference needs an explicit, scoped capability or bounded exception. An optional configured Herma route can use a model within its caller's allowance. An empty queue, malformed payload or missing reviewer does not enable a server model call. The [architecture guide](docs/architecture.md) separates implemented behavior from this migration direction.

## Read next

- [Open-weights training manifests](training/README.md), [requirements-train.txt](training/requirements-train.txt), and [evaluation benchmarks](eval/README.md) ([Dockerfile](Dockerfile) for reproducible build + check).
- [Getting started](docs/getting-started.md): live discovery, access modes and local development.
- [Workflows](docs/workflows.md): a task from claim to receipt, plus product-specific flows.
- [Required checkpoint](docs/architecture-checkpoint.md) and [architecture inventory](architecture.json): nouns, verbs, surfaces and infrastructure boundaries.
- [Status](docs/status.md): repository revisions, CI, deployed Workers and evidence limits.
- [Roadmap](docs/roadmap.md): remaining work and the evidence needed to call it complete.
- [Research for your projects](docs/research.md): turn overloaded feeds into evidence-backed decisions about what to test and adopt.
- [Swarm pilot and creative seeds](docs/swarm-readiness.md): harness results, alternative solutions and launch limits.
- [Fine-tuning workers and research pilot](docs/fine-tuning-pilot.md): actual CPU/GPU smoke and the unrun useful-task comparison.
- [Providers and compute](docs/providers-and-compute.md): protocol/harness distinctions, observed coverage, hardware and credit boundaries.
- [Community seed ideas](docs/community-seeds.md): source-backed mappings and unadmitted noun/verb candidates.
- [Machine-readable snapshot](status.json), [snapshot evidence](evidence/training-and-community-2026-10-29.json), [historical readiness](evidence/readiness-2026-10-29.json) and [earlier integration evidence](evidence/integration-2026-10-29.json).
  - Superseded in part: the snapshot evidence, observed on October 29 at 19:59 UTC, lists pretrained Llama 1B/3B training, Muse Glimmer training and a Kaggle notebook as not run. Later records show all three ran, on synthetic tasks: [Tessera's continuous-tuning record](https://github.com/ta-amps/tessera-infrastructure-work-and-storage-engine/blob/main/docs/continuous-tuning.md) for Llama 3.2 1B and 3B, and the [Muse Glimmer 30B run record](evidence/glimmer-30b-2026-10-29/README.md), which used Kaggle's two free T4 GPUs rather than an H100. Useful-task evaluation and promotion are still not done. The dated file stays as it was recorded.
- [Agent entry point](llms.txt) and [contribution rules](CONTRIBUTING.md).

Run `make check` to validate this guide offline. Built with Llama (Llama 3.2 Community License applies to Llama 3.2 materials). Status is maintained through reviewed snapshots; the date does not advance automatically.