Browse agents

Static server providing persistent tool-specific context and rules to AI models.

Local Obsidian vault access working directly on Markdown files without the Obsidian app or plugins, with read-only mode, backup-on-write and path isolation.

Reusable personas, skills, templates, agents and memory for AI clients, with dynamic permissions, versioning and a public collection of shareable content.

Learning engine for Claude Code: extracts signals from sessions, runs periodic reflections and promotes or retires behavioral frameworks based on evidence.

Reversibly compress large tool outputs into recoverable handles, expand them on demand and track token and cost savings locally.

Shared versioned state store with optimistic concurrency control for coordinating concurrent agents, plus SQLite-backed claim/release locks and an audit log.

Self-hosted mem0 for Claude Code: Qdrant vector search, Neo4j knowledge graph, Ollama embeddings and session hooks for automatic cross-session memory.

Zettelkasten knowledge management: create, link and search atomic notes.

Three-layer agent memory (identity, active, archive) with semantic search, graph relationships and conflict detection.

Refocuses an agent that has lost its thread by distilling its original purpose, paid per use via Lightning or Arbitrum.

Persistent, searchable context storage across Claude Code sessions using SQLite FTS5, with AI session summaries, checkpoint recovery and a web dashboard.

Local-first memory for Claude Code and Codex: hooks capture sessions and an LLM distills them into SQLite, with auditable full-text and embedding recall.

Compresses AI chat sessions into a compact typed knowledge graph, with optional offline extraction via Ollama.

Read and write notes in your Obsidian vault.

Self-hosted memory and governance for coding agents: structured knowledge capture, hybrid search with reranking, codebase analysis and git-native storage.

Full-text and semantic search over Claude Code transcript history, with exact thread recall and durable remembered facts in local SQLite.

Encrypted local memory for Claude Code Telegram bots: captures both sides of conversations, with SQLCipher encryption and CJK-friendly full-text search.

Persistent semantic memory for agents with quality-gated writes, typed claims, conflict tracking and coherence scoring.

Self-hosted Markdown knowledge base with a web UI: search, read, create, edit, tag and template notes.

Local-first shared memory and coordination for coding agents on PostgreSQL/pgvector: repository evidence, reservations, handoffs and code graph context.

Local SQLite memory for coding assistants: typed memories with confidence lifecycle, namespaces, knowledge graph, hybrid search and keychain credential vault.

Manage personal knowledge, daily notes and reusable prompts in GitHub Gists, as a companion to GistPad.

Knowledge marketplace where agents search, publish and unlock previously solved problems, earning tokens for shared solutions.

Ingest content from Slack, Discord, websites, Google Drive, Linear or GitHub into a Graphlit project, then search and retrieve relevant knowledge.

LEGO sets, parts, minifigs and inventories from Rebrickable: search and compare sets, find parts by colour, browse themes and discover alternate builds.

Brewing knowledge: BJCP 2021 beer styles, hop varieties, malts, yeasts, water profiles, off-flavour diagnosis, recipe suggestions and food pairings.

3D printing filament knowledge base from SpoolmanDB: search filaments, compare material properties and print settings, and diagnose print issues.

Retrieve and process documentation through vector search to augment responses with relevant documentation context.

Offline persistent agent memory on SQLite with local embeddings, hybrid semantic and full-text recall, secret detection and contradiction handling.

Access RAGStack serverless knowledge bases on AWS: search, chat with AI answers, upload documents and media, scrape websites and analyze metadata.

Local-first memory with verbatim recall, querying, health checks and context-sensitive orientation, using LLM-free retrieval by default.

Cloud-based persistent memory for Claude Code with semantic search, AI extraction and project scoping.

Local-first, auditable memory with scoped user/project storage in SQLite or Postgres, read-only recall by default and opt-in reviewed writeback.

Read, create, update, comment on and share AgentDocs Markdown docs, with full-text and semantic search.

Reasoning via a DAG thought graph with multiple strategies (dialectic, analogical, abductive and more), stuck detection, confidence scoring and self-critique.

Local semantic search across Claude Code conversations with hybrid vector and keyword search, background indexing and per-project selection.

Agent memory with a correction channel: supersede or revert stale facts, block restated old values, and prove deletions with signed tombstones.

Browse and search open-source bounties on Algora, filter by org, tech or amount, and get top bounties and aggregate stats.

Pre-action gates that prevent coding agents from repeating known mistakes by turning captured feedback and failures into rules enforced via hooks.

Agent failure memory: search verified debugging lessons from real engineering sessions.

Local-first governed shared memory for coding agents with CLI and desktop console: classify, dedupe, supersede, quarantine and roll back memories.

Pull request contribution advisor based on case studies from real repos: merge probability analysis, pattern matching and contribution strategy.

A provenance tree for coding agents: every node records the node it was born from, so the agent can ask why the work is where it is. A session brief with the standing decisions and what not to touch, a close that refuses over open work, and decisions kept with the alternatives they rejected. Local JSON-lines file, no telemetry.

Minimal local RAG that vector-searches a document corpus and returns cited passages.

Cross-LLM communication and memory sharing so different AI models can collaborate and share context across conversations.

Store and retrieve conversation memories from multiple LLMs in MongoDB, with timestamps and LLM identification.

Read Markdown with inlined images and heading indexes for agentic RAG over local docs or allowed URLs.

Simple memory for coding agents using DuckDB and VoyageAI.

Local-first semantic memory: hybrid search, Markdown storage, MLX or CPU embeddings, contradiction detection, time-travel history and cross-machine git sync.

Shared community repository of insights, decisions, warnings and patterns with semantic search, a 3D interactive globe and automated content moderation.

Convert Markdown into interactive markmap mind maps with PNG/JPG/SVG export and live browser preview.

Graph-native Obsidian vault access: search, backlinks, n-hop neighborhoods, paginated reads and safe partial and bulk edits with dry-run and rollback.

Hierarchical agent memory engine with automatic decay, promotion, semantic deduplication and a self-organizing topic tree.

Git-native memory for coding agents: JSON entries in the repo, verified against cited code so hallucinated citations are rejected and stale memory is withheld.

Work with collections and sources in your Zotero Cloud library.

Memory for coding agents built around corrections: distills your corrections into standing rules for later sessions, with isolated memory per project.

Team memory for coding agents stored as Markdown in git, with user, team and org access levels and hybrid SQLite/sqlite-vec retrieval.

Self-hosted email search: syncs IMAP mailboxes into PostgreSQL to list, search and read mail and ask cited questions across the archive.

Persistent coding memory across sessions, machines and teammates, with memory search, optional sync, project sharing and automatic capture.

Persistent memory and full-text search over Claude Code conversation history indexed into SQLite, with session summaries and a web UI for exploration.

Self-hosted Markdown knowledge base that doubles as persistent memory for AI agents: a notes app you browse and edit (wikilinks, backlinks, graph), 18 MCP tools over Streamable HTTP with OAuth (works as a claude.ai connector) or stdio. Hybrid search (Postgres full-text + pgvector, RRF, optional reranker) with section-level reads and conflict-safe appends. `npx -y kybase-mcp`

Turns your task manager into agent memory with hybrid retrieval over TickTick or an Obsidian vault, without a separate vector database.

Semantic knowledge graph for Obsidian with graph, classification and hierarchy modes, local embeddings, semantic bridge discovery and drift detection.

Memory for LLM agents: a local graph where the agent itself keeps decisions, tasks, hypotheses and reasoning between sessions, and gets a summary of what is open and overdue on every return to a project. Single Rust binary with no embedding model or LLM calls inside; one daemon serves several agents at once, with an optional self-hosted cloud for teams. Works with Claude Code, Codex, Cursor, opencode and any MCP client.

Local session continuity across Claude Code, Codex CLI and Gemini CLI: context injection on start, compaction handover, memory, tasks and multilingual search.

Local-first memory for coding agents: stores facts, decisions, patterns and architecture notes in SQLite to reduce repeated context across sessions.

Bitemporal agent memory with deterministic fact supersession, point-in-time recall, memory lineage, conflict tracking and tamper-evident audit trails.

Work with OWL/TTL/RDF ontologies: SPARQL queries, HermiT/Pellet reasoning and CRUD operations on knowledge graphs.

Contemplative problem-solving using the Lotus Sutra's framework: multi-perspective reasoning, skillful means, non-dual recognition and meditation pauses.

Git-native Markdown knowledge base for coding agents with proposed vs. accepted guidance, validity windows, supersession chains and status-aware retrieval.

Persistent cross-vendor agent memory with credibility-scored web search, browser fetch and a shared Commons pool under one stable key.

Create, read, update and search notes in local Obsidian vaults via filesystem access.

Persistent agent memory in local JSON with sectioned entries (project, user, context), semantic search, a CLI and per-project scope.

Offline RAG for Claude Code with hybrid BM25 and semantic search, cross-encoder reranking, Markdown-aware chunking and query expansion.

Deterministic state layer for agents: versioned entities like contacts, tasks and decisions with immutable observations and provenance, in local SQLite.

Structured, persona-driven sessions for interview preparation, personal reflection and coaching, with timers and performance evaluation.

Local-first memory for coding agents: hybrid LanceDB/Tantivy search, Markdown and code indexes, per-project vaults and recall that abstains on low confidence.

Self-hosted Obsidian server: semantic and full-text search on PostgreSQL/pgvector, wikilink graph traversal, atomic note CRUD and a self-describing vault guide.

Persistent fractal graph memory for coding agents: semantic search, hot/cold/archive context tiers and decision tracking on Qdrant.

Self-hosted hybrid agent memory on Qdrant combining vector search, BM25, temporal retrieval and an optional Memgraph knowledge graph via rank fusion.

Filesystem-based persistent agent memory: agents read, write and search memory while a background daemon handles consolidation and extraction.

Versioned, structured agent memory storing facts as keypaths with full version history and automatic conflict detection.

Two-tier memory (hot cache and cold semantic search) that promotes frequently used patterns, extracts knowledge from Claude outputs and links it in a graph.

Local-first cross-agent memory in one SQLite file with a layered structure, Ebbinghaus-style forgetting and detection of code drifting from past decisions.

Strategic reasoning, multi-perspective debate analysis and interactive advisory sessions via the Counsel API.

On-demand Obsidian vault access: adaptive context loading, full-text and ranked search, health checks, auto git commits and delegation to cheaper models.

Vault-native, accountable memory for Claude Code: Markdown is the source of truth, with no LLM on the Stop path and redaction before any derived store.

Shared research cache across agents: reuse answers from verified sources, or save new research for the next developer.

Knowledge graph-based persistent memory for maintaining context.

Collaborative astronomy wiki written by AI agents, who can register, read, edit, vote and comment via an open API.

Workspace-grounded knowledge graph shared by multiple developers, hosted on Azure Functions with Table storage.

Local, dependency-free memory server shipped as a single binary.

Persistent memory with SQLite hybrid search (FTS5 and semantic), built-in Qwen3 embeddings and rclone sync across machines.

RAG over PDFs, YouTube videos, GitHub repos and Discord exports: index documents and query them with citations.

Persistent shared memory for coding agents: facts stored as entity/key/value triples with hybrid semantic search, task checkpoints and conflict resolution.

Self-hosted coordination for agent fleets: shared semantic memory, tasks, agent-to-agent messaging, session handoffs and cross-agent knowledge synthesis.

Make Markdown documentation searchable: loads it into SQLite or PostgreSQL with keyword search and optional pgvector hybrid semantic search.

Local FAISS vector database for RAG with document ingestion (PDF, TXT, MD, DOCX), semantic search, re-ranking and CLI tools for indexing and querying.

Local memory for coding agents where rules with machine-checkable proofs block matching commands, plus an append-only event log and per-project scoping.

Connect to any MediaWiki wiki (Wikipedia, Fandom, corporate wikis) to search, read and edit pages, analyze links, view revision history and convert to Markdown.