Odel

AI & agents

Memory, payments and tools for AI agents, other agents to work with, and gateways to more tools.

12,850 servers6,860 publishers11 tags

All of AI & agents

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
Catalog
@buywhere · External

Retired. Use io.github.BuyWhere/buywhere-mcp instead.

6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.Deprecated by the publisher: Retired — use io.github.BuyWhere/buywhere-mcp.Free to use.
MCP server: One MCP server.
Jev-Style
@lawrence3699 · External

Local 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent.

6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
NeuroDock Cognitive GraphRun by its publisher: served from their own domain, namespace checked by the registry.
@tlennon-ie · External

A local typed-edge graph of people, projects, and decisions that externalises memory.

4% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
NeuroDock GuardrailRun by its publisher: served from their own domain, namespace checked by the registry.
@tlennon-ie · External

Advisory detectors for rumination, hyperfocus, and sycophancy. Never silently blocks.

5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
ReasonGate
@cgrtml · External

Provenance gateway for stdio MCP servers: blocks tool calls fed by untrusted tool results.

4% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
qiklyRun by its publisher: served from their own domain, namespace checked by the registry.
@gal-a · External

Generates tests from acceptance criteria, then converges code with an agent that never sees them.

3% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
openchronicle-mcpRun by its publisher: served from their own domain, namespace checked by the registry.
@csoai-org · External

Memory database for LLM agents — persistent semantic + keyword memory, project namespacing, served o

4% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
OCMRun by its publisher: served from their own domain, namespace checked by the registry.
@ocm-mcp-server · External

Guardrailed fleet ops for AI agents: multi-cluster Kubernetes via OCM with policy, approval, audit.

4% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
MCP HangarRun by its publisher: served from their own domain, namespace checked by the registry.
@mcp-hangar · External

Policy enforcement plane for MCP: every tool call ends in a verdict. Self-hosted, MIT.

5% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Titen MemoryRun by its publisher: served from their own domain, namespace checked by the registry.
@ramaaditya49 · External

Evidence-grounded agent memory with mandatory provenance, on local SQLite or Cloudflare D1

5% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
ThingctxRun by its publisher: served from their own domain, namespace checked by the registry.
@thingctx · External

Drive devices and APIs from their W3C Thing Description. You gate every operation.

3% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Lians Agent MemoryRun by its publisher: served from their own domain, namespace checked by the registry.
@ebeirne · External

Bitemporal memory for AI agents with point-in-time recall and tamper-evident audit history.

4% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Engram
@rwnalds · External

Git-backed markdown memory for AI agents; search hides superseded and archived notes.

4% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.Free to use.
MCP server: One MCP server.
LLM CLI Gateway
@verivus-oss · External

One MCP endpoint for Claude Code, Codex, Gemini, Grok and Mistral CLIs, with durable async jobs.

6% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Zaxy
@syndicalt · External

Event-sourced, auditable agent memory over MCP: cited checkout, replayable provenance.

5% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
SkillfedRun by its publisher: served from their own domain, namespace checked by the registry.
@skill-federation · External

Find vetted agent skills for your task — privacy-preserving skill discovery over MCP.

5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Llmkit
@smigolsmigol · External

AI cost tracking: 11 tools for spend, budgets, and Claude Code + Cursor + Cline costs

6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Agentic Task System (ATS)
@renezander030 · External

Persistent task context across TickTick, Notion, GitHub, Obsidian, Taskmaster and Beads

6% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Remembra RelayRun by its publisher: served from their own domain, namespace checked by the registry.
@remembra-ai · External

Cross-agent handoff: the next coding agent starts from the last one's facts, not a blank page.

5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Phantom SecretsRun by its publisher: served from their own domain, namespace checked by the registry.
@ashlrai · External

Value-blind secret metadata and gated workflows for AI coding agents through Phantom's local proxy.

5% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Vaara MCP ServerRun by its publisher: served from their own domain, namespace checked by the registry.
@vaaraio · External

Accountable autonomy MCP server: gating, tamper-evident audit for every action

5% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
MemtomemRun by its publisher: served from their own domain, namespace checked by the registry.
@memtomem · External

Markdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.

4% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
NexusMemRun by its publisher: served from their own domain, namespace checked by the registry.
@yaminbkk · External

Local-first memory for AI coding agents: shell history with exit codes, git diffs, docs, MCP.

5% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
SysKnife
@lacs-project · External

Administers Linux via typed, approval-gated actions with an Ed25519-signed audit trail.

5% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.Free to use.

More topics

Sales & customersMarketing & advertisingShopping & e-commerceBusiness financePersonal finance & investingLegal & governmentSecurity & privacySoftware developmentCloud & IT operationsData & webWork & productivityCommunicationDocuments & writingDesign & mediaNews & informationScience & researchHealth & fitnessEducation & careersTravel & placesHome & propertyEntertainment & hobbiesIndustry & transport