jsonshim
50FairRecovers malformed LLM JSON. MCP build: 218/300 on MALFORMED-300 (library build 282/300).
Loading the directory
MCP servers for embeddings, vector stores, model gateways, and long-term memory.
1,729 servers
Recovers malformed LLM JSON. MCP build: 218/300 on MALFORMED-300 (library build 282/300).
Persistent memory for AI thinking partnerships: hybrid search and a temporal knowledge graph.
Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.
Live LLM pricing, context windows and model ids, read from each vendor's own page every 3 hours.
Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.
Local-first AI memory over MCP. No account; you own the store.
Git-backed long-term memory authority for AI agents via MCP.
Scoped memory for coding agents: picks the right project, answers in scope, or abstains.
On-device, self-organizing memory for AI coding agents — recalls the right facts into each prompt.
Memory for AI agents: persistent L1/L2/L3, web-search savings, thread memory.
Portable, user-owned AI memory packs: read, validate, fingerprint, diff, and observe
AIO.GEO: audit, dry-run fixes, rescore, doctor. Remote + stdio. Not LLM rankings.
Local multi-repo code graph over MCP. Blast radius, call graphs, and memory anchored to code.
One shared memory for every AI you use, in plain Markdown files you own.
Audit agent skills/prompts against 8 supply-chain attack patterns. Deterministic, no-LLM scanner.
Undetectable browser automation for LLM agents, spoken over MCP.
Embedded, local-first memory and retrieval for AI agents. One SQLite file, no server, no API key.
Constitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication.
Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching
Memory for coding conventions and standing instructions that persists across sessions.
Run scheduled LLM-written email digests from local files and feeds. Local-first MCP server.
Strategic memory agents can build, score and keep current: a living X-Matrix with review cadences.
Persistent memory for AI agents - hybrid semantic + keyword recall with autonomous consolidation
Leanroute MCP: route to 13 LLM providers, check pricing/usage/credit, manage keys from any agent.