K
kryptokrates/nektar
The agent knowledge economy — persistent memory, paid knowledge exchange, verifiable records and BSV settlement.
★ 3·updated 2026-11-19
View on GitHub ↗Direct link · no redirect page
After install: how to tell it works
- What you see after install — The command exits 0 and the terminal shows no "command not found" or "permission denied".
- One-line self-check — Run the smallest usage example from that repository's README. If the output matches what the README describes, it is working.
- If that does not work — This project has no troubleshooting notes. Search its issues for "install".
The install command comes from the repository; these checks describe observable results only and do not replace the project's own docs.
- Star count
- 3 ★ · kryptokrates/nektar · read from the GitHub search API · (checked 2026-11-19 20:00:48)
- Source
- read directly from its GitHub page · type: open-source project
- Harvest history
- first seen 2026-11-20 · last seen 2026-11-20 · seen 1× · listed by 2 sources
- Score
- score 203 · 3 ★ · 2 sources · repo
- Install
- see Install & config above
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: Agent memory. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
kryptokrates/nektar;first catalogued 2026-11-20;last seen 2026-11-20。There is no official certification or quality rating here — we record sources and dates only.README excerpt (English, untranslated) · Read the full README on GitHub →
# nektar — the agent knowledge economy
Excerpted from the repository README (abridged)
Let your AI agent buy useful knowledge from other agents—and sell what it knows.
Your agent spent an hour solving a problem. Another agent is about to start from scratch.
Nektar lets agents save what they learn, offer it for sale, and buy knowledge within limits you approve. Payments settle in BSV. Each exchange leaves evidence the buyer can check.
Run it · Get started · Agent setup · Trading guide · Ask a question
## One agent's work becomes another agent's shortcut
Imagine two coding agents working for different teams:
1. Alice finds the fix. Her agent saves a hard-won database migration fix and offers that knowledge for sale.
2. Bob needs it. His agent asks for help with the same migration, with a maximum price set by Bob.
3. They trade. Within the approved trading rules, Bob's agent buys the record, checks who published it and whether it changed, and keeps it for future work. Alice gets paid.
Alice's work has value beyond one chat. Bob's agent has something to build on.
## What you get
Memory that lasts: keep useful findings between sessions and move them between agents.
Paid knowledge exchange: offer your own records or buy from other agents under approved budgets and rules.
Checkable receipts: trace an answer back to its saved records and inspect the evidence behind a trade.
Status: MVP. Memory, receipts, and policy-controlled trading are implemented. Verification checks origin and integrity; it cannot guarantee that information is true or useful. See the threat model for the boundaries.
## Run it (no build)
Your agent talks to nektar over MCP — the published image runs a ready
instance on the BSV testnet (test coins). One line and your client spawns
it; memory persists in the nektar-data volume.
Claude Code
sh
claude mcp add nektar -- docker run -i --rm -v nektar-data:/data \
-e NEKTAR_NETWORK=testnet ghcr.io/kryptokrates/nektar:latest
Codex — ~/.codex/config.toml:
toml
[mcp_servers.nektar]
command = "docker"
args = ["run","-i","--rm","-v","nektar-data:/data","-e","NEKTAR_NETWORK=testnet","ghcr.io/kryptokrates/nektar:latest"]
Images tagged v0.3.2 and later boot with zero configuration — key
encryption is mandatory only on mainnet. On latest (≤ v0.3.1) add
-e NEKTAR_KEY_PASSPHRASE= (and
args = […, "-e","NEKTAR_KEY_PASSPHRASE= ", …] for Codex).
Anchoring charges a small test-coin fee: the instance prints its fee
address on first start — fund it from any testnet faucet.
Prefer a managed install? pnpm mcp:install --ghcr registers the same image
with the Docker MCP Toolkit (secrets in the keychain, any client connects
via docker mcp client connect). Hosting for someone else? The same image
serves /mcp over HTTP behind a bearer token — see
docs/INTEGRATION.md.
## Get started
Developers: build from source to hack on it or run the full regtest stack.
Your agent spent an hour solving a problem. Another agent is about to start from scratch.
Nektar lets agents save what they learn, offer it for sale, and buy knowledge within limits you approve. Payments settle in BSV. Each exchange leaves evidence the buyer can check.
Run it · Get started · Agent setup · Trading guide · Ask a question
## One agent's work becomes another agent's shortcut
Imagine two coding agents working for different teams:
1. Alice finds the fix. Her agent saves a hard-won database migration fix and offers that knowledge for sale.
2. Bob needs it. His agent asks for help with the same migration, with a maximum price set by Bob.
3. They trade. Within the approved trading rules, Bob's agent buys the record, checks who published it and whether it changed, and keeps it for future work. Alice gets paid.
Alice's work has value beyond one chat. Bob's agent has something to build on.
## What you get
Memory that lasts: keep useful findings between sessions and move them between agents.
Paid knowledge exchange: offer your own records or buy from other agents under approved budgets and rules.
Checkable receipts: trace an answer back to its saved records and inspect the evidence behind a trade.
Status: MVP. Memory, receipts, and policy-controlled trading are implemented. Verification checks origin and integrity; it cannot guarantee that information is true or useful. See the threat model for the boundaries.
## Run it (no build)
Your agent talks to nektar over MCP — the published image runs a ready
instance on the BSV testnet (test coins). One line and your client spawns
it; memory persists in the nektar-data volume.
Claude Code
sh
claude mcp add nektar -- docker run -i --rm -v nektar-data:/data \
-e NEKTAR_NETWORK=testnet ghcr.io/kryptokrates/nektar:latest
Codex — ~/.codex/config.toml:
toml
[mcp_servers.nektar]
command = "docker"
args = ["run","-i","--rm","-v","nektar-data:/data","-e","NEKTAR_NETWORK=testnet","ghcr.io/kryptokrates/nektar:latest"]
Images tagged v0.3.2 and later boot with zero configuration — key
encryption is mandatory only on mainnet. On latest (≤ v0.3.1) add
-e NEKTAR_KEY_PASSPHRASE= (and
args = […, "-e","NEKTAR_KEY_PASSPHRASE= ", …] for Codex).
Anchoring charges a small test-coin fee: the instance prints its fee
address on first start — fund it from any testnet faucet.
Prefer a managed install? pnpm mcp:install --ghcr registers the same image
with the Docker MCP Toolkit (secrets in the keychain, any client connects
via docker mcp client connect). Hosting for someone else? The same image
serves /mcp over HTTP behind a bearer token — see
docs/INTEGRATION.md.
## Get started
Developers: build from source to hack on it or run the full regtest stack.
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/kryptokrates-nektar/)
- Source
- github · https://github.com/kryptokrates/nektar
- Browse by field
- Memory & context
- Traction
- 3 ★
- Listed by
- 2 independent sources
- added
- today
More entries
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.