Obelisk

Local coding agent history search with a desktop browser and agent queries. Runs on macOS, Windows and Linux, with an AGPL-3.0 license.

Obelisk brings coding agent history into one local, searchable index that both you and your agents can use. It's for developers who need to recover past decisions, trace file changes across tasks, or revisit a subagent's findings without digging through separate transcript folders.

It indexes sessions from Claude Code, Codex, GitHub Copilot, DeepSeek Harness, Hermes Agent, Kimi Code, OMP, Pi and ZCode. Conversations, tool calls and supported subagent records share one SQLite database on your machine. Full-text search covers those records alongside registered memories and Claude Code workflow history.

The agent skill lets a coding assistant query that history locally and explain the results in plain language. It can retrieve failed tool calls, a file's session history, or conclusions from earlier work. Agents can also propose Markdown memories for your approval, with links back to the source sessions for future recall.

The companion Electron app gives you a separate way to inspect the same records. Search and project filters sit alongside readable diffs, terminal output and file views. Activity heatmaps and token charts show usage over time, while weekly and monthly recap cards provide shareable views of your work. The app watches transcript sources and refreshes the index as they change.

Obelisk is open source under AGPL-3.0. The desktop app runs locally on macOS, Windows and Linux; prebuilt downloads are available for macOS.

Agent Memory LLM Observability and Tracing macOS Windows Linux Agent Skills Code execution Git integration Human approval LLM tracing Persistent memory RAG

Are you the owner or maker of Obelisk?

Claim this page and we'll verify you by hand. Obelisk gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.

Want more people to find Obelisk?Promote it

Something wrong or outdated on this page?

Similar to Obelisk

View all tools

AgentRQ

A self-hosted AI agent task manager under AGPL-3.0, with remote approvals, scheduling, and support for Claude Code and ACP-compatible agents.

1.1KUpdated 17 hours agoAGPL-3.0

macOS · Web#Agent Client Protocol#Agent Skills#Git integration

AgentRQ is a self-hosted task manager for people supervising AI agents on their own computers. Agents can ask for decisions, report progress, and receive tasks while you follow their work and reply from a browser, phone, or desktop app. It also offers a hosted service; agents run on your machines, while the task dashboard runs on your own server or the hosted service.

Agent MemoryAI Workflow AutomationLLM Observability and TracingMCP Servers and Agent Skills

unleashd

A local AI agent manager that organizes coding conversations and runs swarms with Claude Code, Codex and Gemini CLI. Reads OpenCode sessions too.

12Updated 16 hours ago

macOS · Web#Git integration#Human approval#LLM tracing

unleashd is a local workspace for developers who use several coding assistants and want to manage their conversations and agent swarms in one place. It runs a browser interface and server on your own machine, with orchestration built around Git worktrees. You can review work across projects without keeping track of separate terminal histories.

Agent MemoryAutonomous Coding AgentsLLM Observability and Tracing

HarnessX

An open-source Python AI agent framework with a local web UI, reusable behavior modules, model routing, and MIT licensing.

483Updated 2 months agoMIT

macOS · Web#Guardrails#LLM tracing#Multi-agent workflows

HarnessX is a self-hosted Python framework for developers and researchers building AI agents for coding, research, or assistant tasks. It separates model selection from agent behavior, so you can change memory, tools, or safety checks without rewriting the agent. It's open source under MIT.

Agent FrameworksAgent MemoryLLM Evaluation and TestingLLM Fine-TuningLLM Observability and Tracing

AgentField

Self-hosted AI agent platform for Python, Go and TypeScript, with cryptographic identities, audit trails and LLM support through LiteLLM. Apache 2.0 licensed.

2.6KUpdated 2 days agoApache-2.0

#Distributed execution#Guardrails#Human approval

AgentField is a self-hosted, open source platform for developers building AI agents that need to work together under shared access rules. It runs in your own infrastructure and combines agent execution with identity, policy enforcement and audit records. The project uses the Apache 2.0 license.

Agent FrameworksAgent MemoryGuardrails, Security and SandboxingLLM Observability and Tracing

Hypha

An open-source TypeScript AI agent framework with local and remote adapters, policy controls, checkpoints and replay. Licensed under Apache 2.0.

447Updated 4 weeks agoApache-2.0

#Agent Skills#Code execution#Guardrails

Hypha is a local-first TypeScript framework for developers building AI agents that need controlled tool use, recoverable workflows and an audit trail. It separates the agent's reasoning and planning from the execution layer that enforces policies, approvals and workflow boundaries. It's open source under Apache 2.0.

Agent FrameworksAgent MemoryGuardrails, Security and SandboxingLLM Evaluation and TestingLLM Observability and Tracing

Mastra

8 videos

TypeScript AI agent framework that runs locally or on your server, with memory, MCP, evaluations, and models from OpenAI, Anthropic, and Gemini.

28.5KUpdated 9 hours ago

Web#Human approval#LLM tracing#MCP

Mastra is a TypeScript framework for developers building AI agents and applications on their own servers or inside existing web apps. Its server runs locally or as a standalone deployment; Mastra Cloud provides a hosted alternative. Model routing connects to providers such as OpenAI, Anthropic, and Gemini, so running the framework locally doesn't keep those model requests on your machine.

Agent FrameworksAgent MemoryAI Workflow AutomationLLM Evaluation and TestingLLM Observability and Tracing