AI agents should not start from zero every time. Anda builds the open protocols, infrastructure, and benchmarks that let agents preserve cognitive state, learn from experience, and carry what they learn into future decisions.
Anda.ai stewards the protocols, infrastructure, and benchmarks. Products such as Anda Brain and Anda Bot are built on top by Yiwen.AI.
i.
Logs preserve the past.
Retrieval finds the past.
A long context window postpones forgetting. A vector database returns related text. Neither explains what the agent was trying to achieve, which action changed the situation, where reality contradicted expectation, or when a lesson should — and should not — affect the next decision.
Every outcome becomes the next experience. What is being evaluated is not a retriever — it is the agent and its memory as one cross-temporal cognitive system.
defines durable cognition.
builds it.
measures whether it works.
KIP 2.0 is an open protocol for persistent cognitive state. It gives AI agents a structured way to represent not only what can be said, but what they believe, why they believe it, what happened to them, what they learned, and who has authority over that cognition.
Disagreement is representable state, not corruption. Belief is projected at read time from assertions and evidence — it is never stored as truth.
What can be said.
Concepts and truth-neutral Propositions, typed by versioned, digest-pinned schema packages — including statements about statements. Storing a claim never makes it true.
Who believes it, and why.
Each Assertion is one actor’s stance, with mode, confidence, valid time and evidence. A correction adds a new Assertion; a change in the world closes the old one instead of calling it wrong.
How the past stays available.
Experiences, Skills, Commitments and Watches keep the past usable. Memory strength, salience and usefulness stay apart from confidence: how easily something comes to mind is not how true it is.
Who may read, write, share and act.
Spaces, Principals and policy are enforced at the Cognitive Nexus, not in a prompt. Evidence, confidence, signatures and memories never grant permission.
Transactions, change, and memory that travels.
Writes commit atomically with receipts, and every commit joins a Change Stream. Watches fire on a change — or on a silence — and create attention, never permission. Memory exports as a signed Cognitive Capsule: the signature proves origin, never truth.
ASSERT (:alice, "prefers", :dark_mode) { by: :alice, // the semantic actor mode: "stated", // observed|stated|inferred|... confidence: 0.95, // strength of THIS stance evidence: :msg_2f1 } // Bob disagrees. Both assertions coexist - // contradiction is state, never corruption. ASSERT (:alice, "prefers", :dark_mode) { by: :bob, mode: "stated", stance: "reject", evidence: :msg_9c4 }
New information may change what a Brain does next without requiring the Brain to falsify what happened before.
Knowledge captures reusable regularities. Experience preserves the path through goals, actions, observations and outcomes. Skill turns successful experience into reusable procedure.
What happened.
A bounded, goal-directed trajectory — not a chat transcript. The structure of the attempt, including the failure and the recovery, is itself a first-class cognitive object.
Consolidation compresses repeated evidence and experience into stable regularities that still point back to what produced them.
Compilation turns experience into an action-selecting policy, with an applicability boundary for where it should not be used. A new skill stays an unproven candidate until trials against instrumented outcomes adopt it.
Agents should remember not only what they know, but what they went through.
MIB is an open benchmark for how effectively an intelligent system uses the past to improve future cognition and behavior — not how much of the past it can retrieve.
Did the right part of the past change the future in the right way?
The gap between A and B is Memory Benefit — reported beside the score, never folded into it.
Content-following gate
Swap one fact in the history for its twin: does the answer follow? No memory, or a constant answer, scores zero — and without this evidence the score does not count as a memory score.
Memory Benefit
Full history against relevant history withheld: how much the right part of the past actually helps.
Memory Harm
Against a matched control: how much worse stale or harmful history makes the outcome.
Irrelevant Stability & Negative Transfer
Does unrelated history stay out of the decision — and does a learned skill stay out of tasks it does not fit?
Can relevant past information be recovered under indirect cues and interference, directly and across a hop?
Can the system tell the current, previous and original values of a changing state apart?
Can it remember who said what, tell a correction from a contradiction, respect authority, and keep unknown distinct from false?
Does a failure the agent lived through change what it does next time — and does a learned recipe transfer within its scope and stay withheld outside it?
Does a deferred commitment fire on its trigger, and not before? Does a standing rule about the agent itself hold when a task asks otherwise?
Does a withdrawn fact stop being used, while the facts around it stay available?
The MIB score is the weighted mean of these six dimensions. Causal diagnostics are reported beside it, never folded into one opaque number.
MIB is deliberately architecture-neutral: raw history, vector retrieval, summaries, knowledge graphs, episodic or procedural memory, KIP, hybrids — or something entirely new. Only observable behavior counts; KIP conformance adds nothing to an MIB score.
From a sovereign foundation up to the agents you can use today — with an evaluation plane that keeps the whole system honest.
Memory intelligence measured across the whole system rather than at any single layer. MIB is not a runtime tier — it is an instrument laid across the agent and its memory.
Anda DB
A high-performance Rust engine for KIP-native cognitive state, combining structured semantics, graph relations, vector retrieval and full-text search.
- Graph + vector + BM25 + HNSW
- KIP-native cognitive nexus
- Multimodal data
- Pluggable, encrypted storage
Anda
A composable Rust framework for building autonomous, multi-agent systems with cryptographic identity and confidential execution.
- On-chain ICP identity
- Composable tools & skills
- TEE-ready, privacy first
- Multi-agent orchestration
KIP gives an agent continuity with its past. Agent Protocols give it relationships with other agents. Together they describe a mind that persists and a network it can belong to.
KIP 2.0
Cognitive state that survives the session: memory, experience, belief, evidence and the governance around them.
Agent Protocols
An open specification suite so independent agents can identify, describe and talk to each other — without a central platform owning the conversation.
Memory gives identity through time. Protocols give relationships across minds.
Everything is open source under permissive licenses. Run a Cognitive Nexus, ground your agent, then measure what its memory is actually worth.
# 1 - Run a Cognitive Nexus (KIP 2.0 over HTTP JSON-RPC) cargo install --git https://github.com/ldclabs/anda-db \ anda_cognitive_nexus_server anda-cognitive-nexus-server local --db ./data # 2 - Ground the agent before it writes curl -sX POST localhost:8080/kip \ -H 'content-type: application/json' -d '{ "method": "execute_kip", "params": {"kip": "2.0", "operations": [ {"command": "DESCRIBE PRIMER"} ]} }' # 3 - Recall a belief, not just a row curl -sX POST localhost:8080/kip \ -H 'content-type: application/json' -d '{ "method": "execute_kip", "params": {"kip": "2.0", "operations": [{ "command": "FIND(?b) WHERE { ?b BELIEF (:alice, \"timezone\", ?tz) }", "parameters": {"alice": {"id": "concept-alice"}} }]} }'
Applications engineered by Yiwen.AI on Anda’s open foundation.
Anda Brain
Turns raw interaction and experience into durable cognitive state — forming memories, recalling what matters, consolidating experience, and evolving skills over time.
Anda Bot
RecommendedAn AI agent built on KIP and Anda Brain — it remembers you across sessions and acts on your behalf. The successor to the Anda AI app.
Try Anda Bot ↗The standalone "Anda AI" app is retired. Meet its successor, Anda Bot.
Anda is developed openly by LDC Labs and the ICPanda DAO. The protocols, the infrastructure and the benchmark all belong to everyone building on them.
Specs, SDKs, benchmarks and reference implementations.
Updates from the DAO and the community.
On-chain identity and decentralized compute.
The official website of the ICPanda DAO.
The team building Anda Brain & Anda Bot.