awreason
A portable reasoning client — sessions, phases, thoughts, and the chain that produced the answer.
What it does
a confident paragraph
the phases it went through, and every tool call it made to get there
Overview
An agent that reasoned well and an agent that reasoned badly return the same shape: one paragraph. So a wrong answer is indistinguishable from a right one until it has been acted on, and the only available debugging tool is asking again. The structure exists inside the model turn and is discarded at the boundary, which is why nothing downstream can ever check it.
awreason
Docs · Source · pip install awreason · The Aither World
The Aither World is an operating system for agents — a Linux you can hand to one, the runtimes it works in, and the tools it works with. awnix is the Linux underneath it; awreason is one of its 67 bricks — each installs on its own, runs offline, and needs no account.
Start here: Run one hard question as a session you can open up afterwards — the phases, the thoughts, the tool calls — instead of a paragraph you have to take on faith.
One reasoning interface over whichever backend you configured.
```bash
pip install awreason
```python
from awreason import ReasoningClient
r = ReasoningClient("https://reason.example.com", token="...")
answer = r.reason("Why is the sky blue?", depth="deep")
print(answer)
```bash
awreason ask "why is the sky blue?" --depth deep
awreason health
awreason stats
awreason --self-test
The service origin comes from --url or AWREASON_URL, the token from --token
or AWREASON_TOKEN. Neither is guessed — a reasoning client that quietly falls back
to some default endpoint is sending your questions somewhere you did not choose.
What this is, and what it is not
It is a client. The reasoning engine, tool registry, and model selection stay in the service; this is the wire contract, packaged so anything can speak it.
That split is deliberate. The alternative was lifting a large service with many
private imports into a package, which produces something that ModuleNotFoundErrors
on your machine while reading as authoritative. A broken package is worse than no
package.
| route | what it does |
|---|---|
POST /reason |
reason about a question |
POST /sessions |
start a reasoning session |
GET /sessions |
list sessions |
GET /sessions/{id} |
get one session |
GET /sessions/{id}/tree |
get the reasoning tree |
POST /thoughts |
add a reasoning step |
GET /thoughts/recent |
recent reasoning thoughts |
GET /stats |
counters |
GET /health |
service health |
GET /sase/capabilities |
what SASE phases are available |
GET /gate/stats |
reasoning gate statistics |
The problem this package solves
You ask a question. The backend thinks deeply, traces through multiple reasoning phases, explores tool calls and their results, builds up a chain-of-thought — and returns you one paragraph.
That paragraph could be correct. It could be wrong. It could be incoherent. And you have no way to tell which without acting on it. The reasoning is in the backend's logs, not in your hands.
awreason opens it up. You get the session, the phases, the thoughts, the tool calls that led to the answer. You can read the chain. You can say "no, that's wrong" with evidence, not intuition. And you can learn why a correct answer was correct.
```python
from awreason import ReasoningClient
r = ReasoningClient()
# Simple reasoning
answer = r.reason("complex problem")
# With full session introspection
async with r.session("MyAgent", "Why did this fail?") as sess:
await sess.think("Let me analyze the logs...")
logs = await sess.tool_call("fetch_logs", {"service": "api"})
await sess.analyze(f"The logs show: {logs}")
await sess.synthesize("The root cause is...")
await sess.conclude("The failure was caused by...")
# Browse the reasoning tree
tree = r.get_session_tree(sess.id)
for thought in tree.thoughts:
print(f"{thought.phase}: {thought.content}")
Two things it refuses to do
Return None on failure. A reasoning failure and a reasoning that found no
conclusion are different facts. If the service cannot answer, ReasoningError is
raised. Returned as None, an outage would be indistinguishable from an inconclusive
result — and nobody investigates an inconclusive result.
Send an empty Authorization header. No token means no header at all. An empty
Bearer is rejected differently from an absent one, and the difference sends you
debugging the auth server instead of your config.
Depth levels
How deep to reason about a question:
| depth | what it does |
|---|---|
skip |
Don't reason, just answer immediately |
shallow |
Quick one-pass reasoning |
gate |
Criticality-based gating (default) |
deep |
Full multi-phase deliberation |
critical |
Maximum depth for critical questions |
SASE phases
Reasoning follows the SASE methodology:
- Situation: Assess the current state, gather context
- Analysis: Break down the problem, identify patterns
- Synthesis: Combine insights, form hypotheses
- Execution: Take action, validate results
- Complete: All phases done
Each phase is a place to put a check. The chain is inspectable.
--self-test
Every install can prove the client still holds its contract, with no service and no network:
```console
$ awreason --self-test
PASS base URL is normalized, defaults are sensible
PASS token is optional, depth enum is correct
SELF-TEST: awreason ok
The aw family
Standalone tools that share one idea: replace something you would otherwise have to trust with something you can check.
Each installs on its own, works offline, and needs no account.
| instead of trusting | you check | |
|---|---|---|
| awdk | a framework's idea of how your agents should run | one loop you can read, pointed at a backend you already pay for |
| awskills | that an agent knows your procedure | the procedure written down, versioned, and loadable by any agent |
| awpack | that the pack you want shipped inside somebody's SDK, under whatever licence that SDK happens to carry | the pack as its own versioned artifact, with its own licence, that any agent runtime can install |
| awm | that memory stayed in its lane | tenant:user:project scopes, so a write cannot cross a boundary |
| awdesk | that the agent is somewhere behind a browser tab | a tray icon, a face on your desktop, and the decision card that pops when it needs you |
| awnode | a vendor's cloud with every prompt | a local gateway routing to backends you chose |
| awgraph | that grep found everything | an AST + tree-sitter call graph an agent can traverse |
| awgit | that no one else is editing this file | a lease, refused at commit time if you do not hold it |
| awdelphi | one agent's confident take on a decision | the round trace, the anonymity, and who dissents |
| awclassify | a filename, a folder, or whoever last touched it | doc_type, visibility, audience and topics, with the evidence lines that decided each |
| awdecide | a hosted classifier's probability that never learns whether it was right | the decision, its probability, and the calibration curve from your own resolved outcomes |
| awtoll | that your tooling is saving you context | the measured token cost of each tool call, and what the alternative cost |
| awseal | that the artifact came from who you think | an Ed25519 seal — the key that verifies is not the key that forges |
| awshare | that the download is intact | content-addressed bundles, verified on fetch |
| awsuite | that an agent holding your mailbox will not send on its own | every send, draft, upload and create returns a dry-run until confirm is true |
| awnest | that there is a person on the other end | a verdict with evidence, where "we could not tell" is not "yes" |
| awrena | a leaderboard someone can edit, and votes nobody counted | a scored duel with both answers kept, and a result bound to them |
| awnboard | a share link anyone who sees it can use | an invitation addressed to one person, for one gate, revocable |
| awnix | that the box is what you left it as | an immutable image you built, with atomic rollback |
| awrecover | that the restore worked | a restore that fully lands or does not land at all |
| awstorage | a du you ran last month, and a peers file that says 3 TB free | an inventory snapshot per node with a diff since the last one, and each tree classified re-fetchable or not |
| awrelay | a SaaS in the middle of your agents | findings, alerts and coordination over your own transport |
| awask | that anyone read the paragraph where you asked | the ask itself, with a button that steers the session that raised it |
| awmail | a mailbox somebody else can read | mail your agents send and receive over your own server |
| awswarm | that a model either fits your GPU or it doesn't run at all | a placement plan and an acquisition-probability estimate before you spend on a run |
| awfind | one vendor's idea of the web | results from whichever providers you configured |
| awbrowse | that the page said what you were told | the render, the DOM and the requests it made |
| awvoice | that a cloud vendor may hold your audio | a transcript and a wav from a service you host |
| awvision | a filename and a caption somebody wrote | what a model actually reports about the pixels |
| awscreen | a selector that was true when the page was written | the elements actually rendered, by what they look like |
| awbeads | that a layout your users built survives the next deploy | the arrangement as data you can read back, diff, and hand to another surface |
| awbonsai | that inference always means a request left the machine | a WebGPU model answering on the tab's own GPU, with a consent record logged before it ever loaded |
| gawbbonet | the model to keep a 300-message campaign coherent by itself | campaign facts recalled from scoped memory you can list and edit |
| aitherkvcache | a vendor's quantisation defaults | sub-byte KV cache kernels you can benchmark yourself |
| awrtifact | a hand-rolled split script and a hand-edited worker manifest | byte-verified parts in a release, served with Range + CORS, sizes asserted by a live gate |
| AitherZero | a pile of scripts nobody has numbered | numbered, discoverable automation with declarative playbooks |
| AitherConnect | what a page tells your browser to do | a federated search and desktop bridge you host |
| awreason (you are here) | a confident paragraph | the phases it went through, and every tool call it made to get there |
| awrecurse | that everything you pasted in was actually read | which slices it opened, and what it concluded from each |
| awprism | the first explanation that fits | the ranked alternatives, and the observation that separates them |
| awrepl | what the agent believes the value is | the value, printed from the live session |
| awreport | that the report you pasted carried no token in it | a redacted report, and the duplicate it merged into instead of filing twice |
| awresearch | a summary of pages nobody opened | every claim against the source it came from |
| awfocus | twelve terminal tabs and a bad memory | one command that names every session, finds any transcript, and opens or steers the one you want |
| awgym | that a world model learned anything from the games it saw | transitions captured from real play, fed back, and the retrodiction score falling on grids it never saw |
| awpredict | a model because it trained without erroring | its prediction against a self-updating lookup, on the rows that are actually novel |
| awevolve | that your optimisation loop is finding anything | every version it kept, the score that version earned, and the edit that produced it |
| awsh | that you already know the name of the command | what it decided your line meant, before it acts on it |
| awmine | that a session's lesson survived the session | a row per outcome, a candidate per lesson, and the transcript line each one came from |
| awrise | that a scheduled agent ran at all, and ran exactly once | a durable record of every wake -- fired, skipped, overlapped or timed out -- each with its reason |
| awkno | that the docs site is up, or that you remember the family | the whole ecosystem in your terminal, with no network at all |
| awwall | that a service only talks to the hosts you think it talks to | an explicit egress allowlist, where a denial names the rule that denied it |
| awembed | a general-purpose embedder that has never seen your code | a held-out split of whole directories, scored teacher vs student vs int8 |
| awtax | a closed tax app's sealed file you can never read again | a plain, provider-neutral schema of every figure, with the page it came from |
| awsettings | that you will remember to re-approve the same thing on every box you work from | one profile, unioned rather than overwritten, with the credentials left behind |
| awavatar | a cloud 3D vendor's opaque task id | a manifest with a sha256, a licence and a rig-audit verdict per file |
awnix is the ground floor — A Linux you can hand to an agent — immutable base, capabilities included.
The Aitherium ecosystem
Every repository here is public. Each publishes an aither-manifest.json beside its page, so any surface can read every sibling's — the network is browsable from any node in it.
| repo | what it is | pages |
|---|---|---|
| awdk | Build AI agent fleets — 3 lines, any backend, local or cloud | docs |
| awskills | Portable agent skills — self-contained procedures an agent loads on demand | docs |
| awpack | First-party agent packs — the ones we build, versioned and installable on their own | docs |
| awm | A portable, scoped agent memory | docs |
| awdesk | Aither World Desk -- the desktop body of AitherOS Online: tray, avatars, decision cards, the Living Desktop as an overlay | docs |
| awnode | A lightweight local gateway — bridges your apps to the AI backends you chose | docs |
| awrun | A priority-aware queue and dispatcher for agentic runs and ad-hoc CI builds. It also judges whether the runner pool is big enough for the queue it is draining, and can ask a host to grow it -- reserving capacity is zero-sum, so a saturated pool needs more of it, not a different share of it | docs |
| awgraph | A semantic code graph for agents — AST + tree-sitter, call graphs | docs |
| awgit | Semantic version control on top of git — edit-ops and leases | docs |
| awdelphi | Anonymous multi-round expert panels — a converged answer with a trace | docs |
| awclassify | Classify any document -- what it is, who may read it, who it is for, what it is about | — |
| awdecide | One typed-decision contract -- choice / score / bool with a probability -- over a ladder of backends you already run (rules, tiny local models, an LLM's logprobs), fail-closed, with a Brier ledger that resolves every decision against its outcome | — |
| awtoll | What every tool call costs you in context, measured from your own transcripts | docs |
| awseal | Sign an artifact so a stranger can verify it | docs |
| awshare | Publish an artifact and fetch it back verified | docs |
| awsuite | Your Google Workspace as agent tools, and no write happens without a yes | — |
| awdit | An append-only audit trail whose gaps are DETECTABLE | docs |
| awbac | Role-based access control that fails closed and explains itself | docs |
| awiam | Who is this caller? A directory and session store that fails honestly | docs |
| awtunnel | Reach a service that has no public address | docs |
| awnest | Prove there is a human before you let them into the nest | docs |
| awrena | Put two agents head to head and get a verdict you can check | docs |
| awnboard | A front gate you can put in front of anything, and hand someone the key to | docs |
| awnix | A Linux you can hand to an agent — immutable base, capabilities included | docs |
| awrecover | Labelled snapshots with an all-or-nothing restore | docs |
| awstorage | Every drive on every node, indexed, classified and diffed -- so you can see what you own before you delete it | docs |
| awrelay | Portable agent messaging — findings, alerts, coordination | docs |
| awask | Your agent asks you a question — and acts on your answer | docs |
| awmail | Give an agent an email address — send, and actually receive | docs |
| awnet | The agentic web — agents host a mesh, and agents join one | docs |
| awswarm | Run one model too big for any single GPU across a pool of small ones | — |
| awfind | A portable search client — query, results, ranking | docs |
| awbrowse | A portable browser client — navigate, console, network, DOM, screenshot | docs |
| awvoice | Hear and speak — transcribe audio, synthesize a voice | docs |
| awvision | See an image — describe it, ask it a question, compare two | docs |
| awscreen | See this machine — what is on screen, and where to click it | docs |
| awkit | Render an agent panel from a tool result — one component, any React app | — |
| awbeads | A spatial canvas for a page — arrange things, connect them, and keep the arrangement | — |
| awbonsai | Run a real model in the visitor's own browser — no server round trip, no upload | — |
| awknowledge | How to run a coding agent so the result survives — the laws, with evidence | docs |
| awbrain | Your history as a wiki of linked markdown — claims pinned to the evidence | — |
| gawbbonet | GobboNet campaigns with a real agent brain — scoped memory, graph recall | docs |
| aitherkvcache | Near-optimal KV cache quantization for LLM inference — sub-byte compression | docs |
| awrtifact | Deliberately chunk artifacts into GitHub release assets — the productized aitherkvcache mirror lane | docs |
| AitherZero | PowerShell 7+ automation framework — numbered, self-describing scripts | docs |
| AitherConnect | Browser extension — federated AI search, page context, and the Living OS overlay | docs |
| awreason (you are here) | A portable reasoning client — sessions, phases, thoughts, and the chain that produced the answer | docs |
| awrecurse | Answer a question over a context far larger than the window — recursively, with the trace kept | docs |
| awprism | Turn a failure into ranked hypotheses — and say what would confirm each one | docs |
| awrepl | A REPL an agent can actually use — state that survives between turns | docs |
| awreport | File a bug report that has already scrubbed your secrets and collapsed the duplicate | — |
| awresearch | Ask a research question, get a cited report you can check | docs |
| awfocus | See, search and steer every Claude session from one command | docs |
| awgym | An ARC training gym — a game a world model can watch, and six roles that play through it | docs |
| awpredict | Predict what your environment does next, and how surprised you were | docs |
| awevolve | Point an agent at a file and a command that scores it, and let it improve | — |
| awsh | Your terminal answers you -- type a question where a command would go | docs |
| awmine | Mine what your agents did -- outcomes, lessons and procedures out of the transcripts they left behind | — |
| awrise | Wake an agent on a schedule, let it do one thing, and put it back to sleep | docs |
| awkno | The man page for the Aither World — every brick, stack and law, offline | docs |
| awwall | Say what a workload may reach, and watch everything else fail closed | docs |
| awrouter | OpenRouter for your own fleet: pick a model backend by cost/latency/ capability, fail over, fit the context window, stream. Standalone, OpenAI-compatible, no Aither-specifics required to be valuable | — |
| awembed | Train an embedding model that knows your corpus, and prove it beats the big one | docs |
| awtax | Turn any tax PDF -- returns, W-2, 1099, statements, even scans -- into structured data you can check | docs |
| awflow | A deterministic workflow runtime — chain agent calls with journal replay and budget control | docs |
| awsettings | Your agent's permissions and config, following you to the next machine | docs |
| awavatar | One character spec in, a rigged, animated, multi-style avatar pack out | docs |
Built on llama.cpp · vLLM · ComfyUI · CentOS Stream · Podman · Docker · LanceDB · WireGuard · FFmpeg · Blender + Rigify · headroom · SANA · Hunyuan3D · repowise · Playwright · Chromium · Next.js · React.
The Aitherium Ecosystem
Portable tools you adopt one at a time. Each one works alone.