Early access — cache mode live now

Build on sovereign African AI infrastructure.

Forge gives you API access to a working, epistemically-labelled knowledge corpus — plus the reasoning layer behind CHIKARA — so you can build honest software instead of starting from a blank prompt.

524corpus entries, sourced & labelled
7corpora at launch (incl. Shona)
IRA v2.2epistemic verification engine

Where Forge actually stands

Early access, not a demo.

We would rather tell you exactly what works today than promise something polished and make you find the gaps yourself.

LIVE TODAY

Verified corpus search

524 entries across seven corpora — every answer carries an IRA confidence label (Known / Inferred / Hypothetical) so you know how much to trust it.

LIVE TODAY

Builder accounts & API auth

Register, log in, and query the corpus programmatically today. Session-based auth — no waitlist gatekeeping for this tier.

OPTIONAL

Live-model routing

Cache-mode works with zero setup. Optional backends — Ollama (local), OpenRouter, or a CHIKARA endpoint — when you want coverage beyond the corpus. Not required to start.

What you are querying

A real corpus, not a wrapper around someone else's model.

Every entry was written and reviewed for this platform, then run through IRA before it shipped. Seven named corpora ship today.

524Total corpus entries
7Named corpora
82K+Words of source material
0.97Avg. confidence on KNOWN hits
4IRA epistemic categories
v2.2Reasoning engine version
Software Engineering
80 · architecture, algorithms, debugging
Agentic Systems
80 · agents, ReAct, orchestration
Web & UX
80 · progressive web, accessibility
Game Dev
80 · Godot, simulation, 3D, audio
Multimodal & AI
80 · vision, corpus production
DevOps & QA
80 · testing, deployment, observability
Shona Language
44 · grammar, culture, translation

How it works

Three calls to a working answer.

No SDK required for early access — plain HTTP, JSON in, JSON out.

01

Register

Create a builder account and get a session token.

POST /api/auth/register { "name", "email", "password" }
02

Query

Ask in plain language, optionally scoped to a corpus key.

POST /api/query { "query": "...", "corpus": "software_engineering" }
03

Labelled answer

Every response includes an IRA label and sources — never a bare string alone.

{ "ira_label": "KNOWN", "confidence": 0.97, "sources": [...] }

The reasoning layer

Every answer tells you how sure it is.

Forge uses the same Immaculate Reasoning Atom (IRA) engine that grades confidence across CHIKARA products. You get a classification — so your app can decide what to trust, what to flag, and what to reject.

Open the full factor weights, risk zones, and interactive demo on the metrics reference page.

Open metrics reference →
KNOWN P > 0.95 — act with confidence
INFERRED 0.70–0.95 — act, keep verifying
HYPOTHETICAL 0.30–0.70 — flag for review
UNVALIDATED ≤ 0.30 — do not act on this alone

Sibling surface

Cultural Reasoning API — score risk, classify claims.

A separate FastAPI surface: Eighteen Factors weighted risk (0–100) and IRA claim classification. Not a substitute for the 524-entry corpus — a companion for high-stakes human context.

SCORE

Eighteen Factors

POST factor scores. Receive normalised risk, zone (GREEN / YELLOW / RED), and top contributors. Ubuntu/Dignity remains the heaviest weight.

POST /score { "context_label", "factor_scores" }
IRA

Classify a claim

POST a claim and probability. Receive KNOWN / INFERRED / HYPOTHETICAL / UNVALIDATED.

POST /ira/classify { "claim", "probability" }
ASSESS

Combined

Scoring + optional IRA + Four Prerequisites warning when dignity and honor both run high.

POST /assess → zone + IRA + warning

Try the metrics demo (client-side) →

Framework credits: Eighteen Factors — Rodney Vianté Keliana; IRA — Rodney Manyakaidze. Deploy the scoring API from its own package when you need those endpoints live.

What is next

Built in the open, shipped in stages.

LIVE NOW

Cache-mode corpus API

524-entry verified corpus, builder accounts, IRA-labelled query responses.

AVAILABLE WHEN CONFIGURED

Live-model inference routing

Point optional queries at Ollama, OpenRouter, or a CHIKARA endpoint. Default remains cache-only so builders are never blocked on a paid key.

ON THE ROADMAP

Usage dashboard & team seats

Query history, per-domain tracking, multi-user builder accounts.

ON THE ROADMAP

Framework licensing

License the IRA reasoning layer into third-party products, not only CHIKARA's.

Access

Free to start building today.

Early access is open — real builders finding real gaps beat a polished waitlist page.

Explorer

Free
  • Full corpus search access
  • IRA-labelled responses
  • Cache-mode queries
  • Community support
Start free

Institution

Custom
  • Framework licensing
  • Dedicated deployment support
  • Custom corpus domains
Talk to us

Questions

Frequently asked

Is Forge usable right now?

Yes. Register, authenticate, and query a real 524-entry corpus today. Optional live-model backends are configuration, not a blocker.

What if I ask something outside the corpus?

You get an honest lower-confidence label rather than a fabricated fact. With Ollama, OpenRouter, or a CHIKARA endpoint configured, routing is available; otherwise the corpus answer (or honest low confidence) is what you get.

What is IRA?

The Immaculate Reasoning Atom — CHIKARA's confidence grading. See the metrics reference for bands, Eighteen Factors, and a live demo.

Is the Cultural Reasoning API the same as Forge search?

No. Forge search hits the verified corpus. The Cultural Reasoning API scores situations (Eighteen Factors) and classifies claims (IRA). Companion tools — not one product pretending to be both.

Get started

Africa needs builders — not only users.

Register a Forge account and query the corpus in minutes. Study the metrics when you need the scoring layer.