belief-revision 开源项目推荐（45 个）

RichSchefren /atlas

Open-source local-first cognitive memory. AGM-compliant belief revision (49/49 postulates). When a fact changes, downstream beliefs are automatically re-evaluated, not just flagged.

IndelibleVivi /agent-memory-study

Source-linked readings and reproducible studies of agent memory, belief revision, and experience reuse.

agentralabs /agentic-memory

Persistent cognitive graph memory for AI agents — facts, decisions, reasoning chains, corrections. 16 query types, sub-millisecond. Rust core + Python SDK + MCP server.

angelnicolasc /epica

Embeddable Rust runtime for formal AGM belief revision in LLM agents — dual-process uncertainty quantification, C=(P,I,G,R) behavioral contracts, 9 Mnemonic Sovereignty primitives, MCP 2026 native, PyO3 SDK.

rabbiveesh /endoxa

ἔνδοξα — agent memory that stores beliefs, not facts: append-only, defeasible, frontier-resolved

GhostPawJS /codex

Memory for AI agents: beliefs with a source, a certainty and a revision history. SQLite, zero deps, MCP server.

Cartisien /cogito

Agent identity, lifecycle management, and belief revision for AI agents

aLIZELI /belief-merge

Provenance-retaining cross-session context merge for DeepSeek Harness — a confluence theorem with a counterexample, and a benchmark for it.

Zedrichu /Belief-Revision-Agent

Implementation of an AI agent performing belief revision (using belief base entrenchment contraction and expansion)

optakt /lumen

A belief store for reasoning under uncertainty — typed epistemic frames, AGM revision, credal sets, and retrodiction-aware decay

nickjlamb /observer-zero

Can AI agents discover that the laws of their world have changed? An instrumented artificial world where LLM scientist societies run experiments, exchange letters, and form beliefs under hidden ground truth — seeded batteries, frozen manifests, and provenance-checked evaluation. 235 runs across two studies; combined paper under review.

mnemebrain /mnemebrain-benchmark

MnemeBrain Benchmark Suite (BMB): 48 tasks evaluating belief dynamics in AI memory systems — contradiction detection, revision, provenance, and temporal reasoning.

yufanana /ArtificialIntelligence02180

DTU course 02180 Introduction to Artificial Intelligence, Spring 2024

mnemebrain /mnemebrain-sdk

Pyton SDK for MnemeBrain — a belief memory system for AI agents. Supports MnemeBrain Lite and Full APIs.

AXIOVEX /epistemic-ledger

A living epistemic ledger: append-only conclusions with fluid certainty scores, revised as new facts arrive.

atakanelik34 /Bilinc

Hosted memory for AI agents: commit, recall, revise, snapshot and roll back agent state with provenance. Python SDK, CLI and MCP server. Free, no card required.

Verace-Pvt-Ltd /agentic-memory

6-layer persistent memory (sensory, working, episodic, semantic, long-term, procedural) with non-destructive belief revision and injection-safe context synthesis — an MCP server for Claude Code, Cursor, Antigravity, Codex CLI, and any MCP-compatible agent.

onfire7777 /Mnemosyne

Building world-class AI memory: open-source, local-first memory for AI agents with evidence, hybrid retrieval, and MCP. This is the official best ai memory in the world, as seen on bridgemind.

kadubon /record-absence-poc

Auditable finite PoC for preference reorganization under record absence on a fixed comparison frame, with disclosure updates, bounded-coupling certificates, and machine-readable manifests.

soyebmohammad03-dev /MEMORIA

Reproducible laboratory for studying AI memory over long horizons: provenance, replay, contradiction, forgetting, calibration and autopsy.