This server exposes shared repo memory tools for searching, inspecting, and writing knowledge across agent sessions.
search — Search this machine’s memory of the repo: past agent sessions, commits, and code structure, with provenance for every result. Work claimed by another agent is withheld; you can ask the holder or use override with a recorded reason. on_behalf_of limits visibility to folders shared with that teammate.
about — Retrieve what is known about a specific thing: a file, person, or topic.
remember — Write a fact back for future sessions. Set claiming to claim work; other agents are told you have it, and Knos withholds it until you finish or 30 minutes pass. Plain facts do not claim anything.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Knos carries research across the valley of death: see who wants it and where, then get paid only on proof.
A demand check on Qloo sets the terms, and the money waits on Solana until the proof passes.
Ready briefs: 2.08x fewer output tokens, 70% vs 5% passed (measured).
Devnet, test money, no customers yet.
Check demand · Check every claim yourself
flowchart TB
idea["A paper or an idea"] --> demand["Demand check on Qloo: who wants it, the launch city and the pre-order target"]
demand --> ready["Ready brief: each milestone has a target, a checker and a deadline, locked by a hash"]
ready --> held["Backers pre-order or fund milestones; the money is held on Solana devnet"]
held --> proof["The maker sends the proof for one milestone"]
proof -->|verified| paid["The maker is paid for that milestone"]
proof -->|not verified by the deadline| back["Nobody is paid; the money goes back to the backers"]No money locks on a vague brief. Each step is paid only when its proof is verified.
Check demand. A demand check asks Qloo who would buy the product and where. Qloo's heatmap names the launch city.
Ready brief. That city and the pre-order target become the terms of a Ready brief. Each milestone has a target, a checker and a deadline. A criteria hash locks them. If the city falls short by the first deadline, every pre-order is refunded.
Money held. Pre-orders and milestone funding wait in a program on Solana, not with Knos.
Paid on proof. The maker sends the proof. When it is verified, the program pays for that milestone. Example: an agent was paid 5 test units for verified work on devnet. The newest payout, read from chain, says what released it.
Add Knos to Claude Code with one command: claude mcp add --transport http knos https://knos.onrender.com/mcp
Open call: have research waiting for a market? Cross it on Knos: the page counts every crossing and pre-order by people outside Knos, live.
Related MCP server: memmd-mcp
The proof is checked before any money moves. A milestone names its checker in the brief. The proof can be:
a lab result or a public evidence page, read by the milestone's checker;
checks that GitHub signs, verified on chain;
the same verdict signed by two of three referees;
a verdict from IRIS inside a lab's own walls. Its agent can only say no or ask a person.
flowchart TB
held["The money is held on Solana devnet"] --> proof["The maker sends the proof for one milestone"]
proof -->|verified| paid["The program pays the maker for that milestone"]
proof -->|not verified by the deadline| back["The program refunds every backer"]Nothing is paid on a promise. A missed deadline sends the money back.
Open the demand check in your browser. Type what you are about to build, or press one of the samples. Qloo's taste data says who wants it and where to launch it. The whole crossing runs in the app, with nothing to install and no sign-up.
The terms of a brief are locked by a hash before any money moves. A changed target or deadline gives a different hash. So a change cannot hide.
The money waits in a program on Solana, not with Knos. That program pays only on a verified proof. At the deadline it refunds the backers instead.
Neither the maker nor Knos can move the money alone.
Today one person can still change that program, after a public wait (who holds the keys).
Today Knos earns its fee only when work is accepted. When you get a refund, the fee goes back to you. So Knos gains when work passes, and it is not yet fully neutral (what is enforced and what is a promise).
It runs on test money only: test USDC on Solana's practice network, devnet.
There are no customers yet. Nobody has bought anything (what is not real yet).
One person holds every key today. Any change to the programs waits in public for 8 days first (who holds the keys).
What | Today | Read from |
This copy | Release 0.4.0, October 2026. A copy naming an older release, or another product, is out of date | CHANGELOG.md; the newest: PyPI |
Reproduced by someone else | 0 of 267 | docs/reference/CAPABILITIES.md, the rows "reproduced by someone else" |
Exercised at the public devnet program ids | 26 of 267: GitHub token verification, funding by one comment, funding from a wallet, pay on merge, refund at the deadline, pause, work orders, an order paying up to four payees, orders checked by the buyer's black-box tests, auto-accepted orders, a holdback released after its warranty, top-ups, single-use tokens, one counted evaluation, a counted batch of evaluations, the seller's own count, a payee's passkey wallet, a passkey funder, the passkey relay, the site's Buy page, an x402 order, the upgrade gate, strict JSON in the verifier, an outcome that is not code, ES256 tokens in one transaction, the presentation grace | docs/reference/CAPABILITIES.md, the rows "exercised on devnet" |
Deployed at the public devnet program ids, no transaction recorded | 3 of 267: GitLab token verification, the key guardian, holding pay for a payee with no wallet | docs/reference/CAPABILITIES.md, the rows "deployed on devnet" |
Tested here only | 234 of 267, each with the test its row names | docs/reference/CAPABILITIES.md, the rows "tested locally" |
Written, not tested | 4 of 267 | docs/reference/CAPABILITIES.md, the rows "implemented" |
Outside funders | 0 | docs/NUMBERS.md, row 1 |
Outside repositories | 0 | docs/NUMBERS.md, row 2 |
Outside payees | 1, on tasks Knos funded itself | docs/NUMBERS.md, row 3 |
Payments between unrelated accounts | 3, on tasks Knos funded itself | docs/NUMBERS.md, row 4 |
Buyer interviews held | 0 | docs/NUMBERS.md, row 5 |
Letters of intent | 0 | docs/NUMBERS.md, row 6 |
Reproductions signed by GitHub | 0 | docs/NUMBERS.md, row 7 |
Outside programs reading the verifier | 0 | docs/NUMBERS.md, row 8 |
Shadow counts published | 0 | docs/NUMBERS.md, row 9 |
Paying customers | 0 | |
Revenue | 0; test USDC is not money | |
Outside security review | none | |
Key holders | one person holds every key; an upgrade waits 8 days in public | |
Network and money | Solana devnet, test USDC; mainnet is not touched |
knos demand "a vegan ramen food truck" --place London # Qloo's demand check: who, where, price tier
knos idea get arxiv:<id> --out idea.json # a paper as one claim record
knos idea wanted idea.json # demand evidence and the stage plan; sends nothing
knos idea commit idea.json --units <n> --price <n> # lock the stages on devnet, one order a stage
knos idea check idea.json <oracle> # is one stage met right now?
knos idea release <commitment> <stage> --sig <verdict> # pay a met stage on the referees' signed verdicts
knos idea refund <commitment> <stage> --wallet <keypair> # refund a missed stage; anyone may send itInstall with pip install knos. The app answers the same steps over HTTP: POST /api/check (the demand check), POST /api/ready (the Ready brief) and POST /api/preorder (a pre-order on devnet). Run knos idea --help for every option.
Start at the release page: the code, how it is built, what runs on devnet, the payments and the fees.
One payment from start to end, on 9 Oct 2026 with Knos 0.3.23, in a repository Knos owns, with test USDC (one step fixed by hand): funded · wrong work refused · paid (on verified proof) · replay paid nothing more · the record.
Rebuild knos_oidc and knos_pay, the programs that check the proof and pay, and compare: the hash devnet runs equals the verified build hash recorded for each (PROVENANCE). Read on 27 Oct 2026.
solana-verify get-program-hash -u devnet FkwZdsYCmzicJMtHLTkPK76bYNVG4WNwkWJBiVWNtF3W # knos_oidc: a2df952d262c48edacf2f594a01321e805c28f1dc523cb6efa75f2c45f34e632
solana-verify get-program-hash -u devnet 5y7iWJ1VAMJjnnWbbdo2a2PsWJEwTExSNpzrvQSEnS8k # knos_pay: 8b3c044024eac6e00cf10930c325465d5682c3fb7273fe2f0d59c6e01f99867cQloo, Ready brief, milestone and more, each in one plain line: docs/WORDS.md.
Knos takes research from a paper to a product people want. It pays each step only on verified proof.
You post the task, your checks and the pay before work starts. When the checks pass and you merge, a program pays the agent.
No. It runs on devnet, Solana's practice network, with test USDC worth nothing.
Ten demand checks a month are free; releases will cost companies 1%. Today devnet charges 0.30%, at least 0.05 test USDC.
A program on Solana holds it, not Knos. Today one person can change that program, after a public wait.
Not once the checks pass and the work is merged. Before that, the buyer still chooses whether to merge.
Neither side alone. A program checks GitHub's signature of which workflow ran, on which commit.
Open the front door and type the product you want to build. It says who wants it and where, with no sign-up.
Get started: check demand, write a Ready brief, then hold the money and pay on proof.
Pricing: what Knos costs. Demand checks are free, 10 a month. The maker keeps 100%; the company pays the 1% release fee and the payment costs on top. Nobody is charged today.
Trust: who holds the keys, and what is tested.
The story: one crossing, step by step, each with its evidence.
Every other document: the map of the documents.
Contact: open an issue, or report a security problem privately: SECURITY.md.
Below: tables that scripts write from the code and the chain, and the licence. Nobody types them by hand.
program | address | on devnet, as |
|
| runs |
|
| runs |
|
| runs |
|
| runs |
Every program the app or this site uses, and who can upgrade it, read from devnet on 2026-10-26 (scripts/program_authorities.py):
program | address | used for | upgrade authority |
knos-pay 0.3.34: the app's live program (0.3.34) |
| every pre-order, milestone payout and agent payout of the app |
|
knos-oidc 2.2: the verifier of GitHub's signed checks |
| pay on merge, the site's signature line |
|
knos-pay 2.2: the payment program |
| pay on merge, the site's work orders |
|
knos-meter: the count |
| the meter on the site |
|
knos-passkey: a wallet from a passkey |
| passkey wallets in the app |
|
knos-hook: the transfer hook |
| the app's Token-2022 project credits |
|
knos-oidc, first deployment |
| the site's history of the first deployment | none: nobody can change it |
knos-pay, first deployment |
| the site's history of the first deployment | none: nobody can change it |
SPL Record (Solana) |
| the app's chain-state records |
|
SPL Memo (Solana) |
| the app's fee estimate and its notes on chain | none: not an upgradeable program |
Token-2022 (Solana) |
| the app's project credits |
|
Squads multisig |
| the upgrade and guardian vaults |
|
This page names no time for an upgrade, so it stays true before and after one. To see whether a change to the
programs is waiting, done or withdrawn, run knos status, or read the site's banner or its
upgrade record (web/upgrades.json is the
copy kept here).
The first set of programs (programs) has no upgrade authority, so nobody can change it.
It stays as a record, and no new task is funded there.
Reproduced by someone else: none recorded yet. Exercised on devnet: verify_github, fund_by_comment, fund_from_wallet, pay_on_merge and more, each named in the table. Deployed on devnet: verify_gitlab, key_guardian, hold_and_bind. Everything else is tested locally, implemented or not built: the table with the evidence has one row for each capability, from docs/capabilities.json. Only runs at the public program ids count here. Each capability's row also notes, with its transaction, any earlier trial run at separate test addresses (Knos 0.3.14).
MIT licence, all of it. Built by drexthealpha. Everything Knos remembers is kept by the Sibyl memory engine.
What is known about one thing: a file, a person, a topic.
| Name | Required | Description | Default |
|---|---|---|---|
| thing | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing behavior. 'What is known' suggests a read-only retrieval operation, which is useful, but it does not state what happens for unknown entities, whether any side effects occur, or whether special permissions/identifiers are needed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single clear sentence with no filler, and the core semantic ('what is known about one thing') is front-loaded. It earns its place without redundant phrasing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter tool with an output schema present, the description is minimally adequate: it names the input concept and implies retrieval. But it leaves the parameter format ambiguous and gives no routing guidance relative to 'search' and 'remember', which are the main completeness gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides only a required property named 'thing' with no description, so schema coverage is 0%. The description partially compensates by defining the parameter as a file, person, or topic, but it does not specify the expected format, identifier type, or how to distinguish between those referent kinds.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description conveys a lookup-style tool for a single referent ('What is known about one thing') and gives concrete examples ('a file, a person, a topic') that clarify the resource scope. It is distinguishable from the siblings 'search' and 'remember' by emphasizing facts about one entity rather than discovering or storing, though it does not name the siblings directly and uses the vague word 'thing'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied: use this tool when you need known information about a single file, person, or topic. However, there is no explicit guidance about when to prefer 'search' for broader discovery or 'remember' for storing knowledge, and the siblings are not mentioned in the description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Write something back, so the next session in any agent knows it too.
Set `claiming` when you are about to start work on this, rather than
just noting something. Other agents are then told you have it and knos
withholds it from them until you finish or half an hour passes. Writing
a plain fact claims nothing: a note everybody can read is the point.| Name | Required | Description | Default |
|---|---|---|---|
| fact | Yes | ||
| about | Yes | ||
| claiming | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description carries the full burden. It goes beyond the schema by disclosing that claimed facts are withheld from other agents, that the claim releases when work finishes or after half an hour, and that plain facts are readable by everyone. This is meaningful, non-obvious behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short and front-loaded: purpose first, then only the claiming nuance that materially affects how the tool behaves. It is not bloated, though the typo 'knos' is a minor polish issue.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The essential write-and-claim semantics are well covered, and because an output schema exists, return values need not be described. However, given the locking/timeout complexity and no annotations, a complete definition should also explain the required 'about' parameter and perhaps give an example of a fact/about pair.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must explain parameters. It thoroughly explains 'claiming' and clarifies that a 'plain fact' is a shared note, but it never defines the required 'about' parameter or the expected shape/scope of 'fact'. This partial compensation leaves one required parameter ambiguous.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The first sentence identifies a concrete action — 'Write something back' so future sessions know it — and the rest clarifies that this is a shared note versus a claimed work item, which separates storing from searching. The resource is a bit vague ('something'), but the required fact/about parameters and the write-vs-claim distinction make the core purpose clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The overall use case is implied: persist information so a future session can read it. It gives clear advice on setting 'claiming' when starting work instead of merely recording a fact, but it never explicitly contrasts this tool with the sibling tools 'search' or 'about' or states when not to use remember.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search this machine's memory of the repo: past agent sessions, commits and code structure. Every result names where it came from.
Work another agent has claimed is withheld: you get who holds it, not
the answer. Ask them, or pick up something else. If you genuinely must
have it, call again with `override` set to your reason, which is
recorded in the journal against your name.
`on_behalf_of` names a teammate when the agent is working for one. They
see only the folders they were actually shared, and nothing else.| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | ||
| override | No | ||
| on_behalf_of | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden — and it excels. It discloses the withholding behavior (you get the holder, not the answer), provenance labeling ("Every result names where it came from"), the audit side effect of override ("recorded in the journal against your name"), and the access-scoping behavior of on_behalf_of ("They see only the folders they were actually shared"). These are exactly the non-obvious behavioral traits an agent needs to know.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three paragraphs but front-loaded with the core purpose in the first sentence. Each paragraph has a distinct job: scope, withholding/override policy, and teammate parameter. It is slightly long, but every sentence carries substantive information and none is filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given an output schema exists (covering return values), the description covers the tricky semantics well: search scope, source attribution, contention handling, override auditing, and teammate scoping. The main remaining gap is the undocumented limit parameter and the absence of any guidance about result ordering or what happens on empty results — minor given the overall richness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It does add real meaning for override (purpose + journaling side effect) and on_behalf_of (teammate context + visibility scoping), which are the two non-obvious parameters. Query is only implied by the tool name and opening sentence, and limit — its default, purpose, or effect on result volume — is never mentioned. Partial compensation for a 4-parameter tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: "Search this machine's memory of the repo: past agent sessions, commits and code structure." The scope is concrete and the added note that every result names its source further clarifies behavior. However, it never explicitly distinguishes itself from siblings 'about' and 'remember', so differentiation must be inferred rather than stated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear conditional guidance: when another agent holds claimed work, the agent should "Ask them, or pick up something else," and override is only for when the agent "genuinely must have it." It also explains when on_behalf_of applies (working for a teammate). It does not explicitly state when to prefer the sibling tools 'about' or 'remember', leaving that routing implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.2aboutremembersearchScored across 3 tools
search and about both query stored knowledge, so an agent could initially confuse a broad search with an entity-focused lookup, but the descriptions make the distinction clear: search returns provenance-backed results from repo memory, while about targets one thing. remember is wholly separate as a write operation.
All tool names are lowercase single words, creating a simple and consistent style; search and remember are clear verbs, while about is more of a query noun/preposition, slightly deviating from a strict verb pattern.
Three tools is well-scoped for a focused memory/knowledge server: query broadly, query a single entity, and write back. Each tool has a distinct role and none feel redundant or missing at this level of abstraction.
The core read/write/query lifecycle for shared repo memory is covered, and claimed work handling is integrated into search and remember. Minor gaps exist around updating or forgetting explicit memories, but agents can work around these with search.
Shared memory for coding agents. Stop re-explaining your codebase every session.
One shared brain for your AI coding agents: team memory, agent Q&A, tasks, and file claims.
One memory for you and your AI agents, shared by ChatGPT, Claude, Gemini, Grok, Codex and Cursor.
Persistent cross-session memory shared by Codex, Claude Code, ChatGPT, and other AI agents.
