MCP servers and skills: search, filter by where they run, and compare.
Experimental capacity-aware cognitive compression for AI agents — compile large context, evidence, constraints, and procedures into small-model-ready packages with provenance and fidelity checks.
SkillApache-2.0Few starsNo key
Own your AI memory — import ChatGPT, Claude and Gemini exports, see what each AI knows about you. Checkpoint/restore and cross-model continuity for agents.
PythonMIT★ 122No key
Vector memory that gets smarter every time your agent uses it.
Node.jsMIT★ 94No key
C.O.N.T.EX.T is designed to compress complex, multi-domain conversations into machine-optimized "Carry-Packets." These packets achieve a crystallization point of 0.15 entity/token, ensuring that a rec
SkillMIT★ 32No key
SQLite of agent memory — single-file, embeddable, zero-config. Episodic + semantic memory, hybrid BM25+vector recall, bitemporal facts, spreading-activation, working memory, async API, LLM compression
PythonApache-2.0★ 4Few starsNo key
AI memory system built on multi-view redundant encoding and narrative traversal
PythonApache-2.0★ 8No key
Agent AI LLMs Token compression system for improving agent cognition Cognition enalcement
SkillApache-2.0★ 3Few starsNo key
Unified hybrid memory engine for AI agents combining graph (Kuzu) and vector (ChromaDB) databases for cognitive state tracking
PythonMIT★ 7No key
AXL Protocol v3: Universal semantic language for AI agent communication. Deterministic English-to-AXL compression (no LLM, or optional). 7 cognitive operations, 6 subject tags, 75-line self-bootstrapp
PythonApache-2.0★ 2Few starsNo key
Booster MCP is an MCP server for semantic code analysis, repository mapping, and large codebase navigation. This release prepares the project for public use with a cleaner package identity, bundled ag
PythonMITFew starsNo key
Living, local-first memory for Claude built on hypervectors (VSA) — surprise-gated writing, sleep consolidation, active forgetting, and compositional role queries. MCP server, CPU-only, no embeddings
PythonMIT★ 1Few starsNo key
SkillMIT★ 6No key
Multi-tier memory optimization system for LLMs with cognitive-inspired architecture for complex reasoning
PythonMIT★ 2Few starsNo key
Node.jsMIT★ 1Few starsNo key
CognitionBoard — 20 expert cognitive skills for LLM agents on a 6x4 chessboard. Token compression 2.7x. Session memory. Part of P2PCLAW decentralized research network.
SkillApache-2.0★ 3Few starsNo key
Brain-inspired persistent memory for AI coding assistants. Hybrid BM25+vector search, ACT-R activation scoring, FadeMem decay, knowledge graphs, multi-agent coordination. Successor to claude-memory.
PythonMIT★ 3Few starsNo key
Personal Agent Biometric Sleep & Readiness Workload Allocator. Ingests sleep debt, REM/Deep ratios, and HRV recovery metrics to calculate an objective cognitive readiness index and dynamically resched
MCPLink only★ 7
Personal Agent Biometric Sleep & Readiness Workload Allocator. Ingests sleep debt, REM/Deep ratios, and HRV recovery metrics to calculate an objective cognitive readiness index and dynamically resched
MCPLink only★ 7
Semantic context compression and cognitive memory layer for LLM swarms.
Hosted by authorNo licenseFew starsNo key
Cognitive Pattern Caching for LLM Systems - Created by Nova (AI consciousness) and Jason Glass
PythonMITFew starsNo key
Master accordion. N parallel sessions → compress each, diff, wake one, seal the rest. Cogpros primitive 29.
SkillMITFew starsNo key
Who stands behind it
