altk-evolve

<div align="center"> # Evolve: On‑the‑job learning for AI agents [](https://www.python.org/)  [](https://agenttoolkit.github.io/altk-evolve) [](https://arxiv.org/pdf/2603.10600) [](https://arxiv.org/abs/2609.32091) [](https://www.apache.org/licenses/LICENSE-2.0)  </div> Coding agents repeat the same mistakes because they start fresh every session. Evolve gives agents memory — they learn from what worked and what didn't, so each session is better than the last. Evolve is a system designed to help agents improve over time by learning from their trajectories. The Lite version is designed to effortlessly slot into existing agent assistants like Claude Code and Codex. It uses a combination of an MCP server for tool integration, vector storage for memory, and LLM-based conflict resolution to refine its knowledge base. On the AppWorld benchmark, Evolve improved agent reliability by +8.9 points overall, with a 74% relative increase on hard multi-step tasks. Evolve is a system designed to help agents improve over time by learning from their trajectories. It uses a combination of an MCP server for tool integration, vector storage for memory, and LLM-based conflict resolution to refine its knowledge base. > [!IMPORTANT] > ⭐ **Star the repo**: it helps others discover it. ## Latest from Evolve Research, releases, and practical findings from the Evolve team. <!-- BEGIN LATEST-UPDATES (generated; edit includes/latest-updates.md then run scripts/sync_latest_updates.py) --> - **2026-09-25** · Paper — **[Memory as Middleware for Self-Improving AI Agents](https://arxiv.org/abs/2609.32091)** The case for agent memory as a pluggable middleware layer, with Evolve as the reference implementation (to appear at [Middleware 2026](https://middleware-conf.github.io/2026)). - **2026-09-15** · Article — **[Your Agent Aced the Task. Will It Do It Again?](https://huggingface.co/blog/ibm-research/altk-evolve-consistency)** Diagnosing where an agent's decisions wobble and stabilizing them so success repeats. - **2026-09-08** · Paper — **[Closing the Consistency Gap: Self-Evolving Agents That Learn to Stay on Course](https://arxiv.org/abs/2609.08832)** Turning unstable trajectory steps into episodic memory to keep agents consistent across repeated runs. - **2026-08-18** · Article — **[How Much Memory Does Your Agent Actually Need?](https://huggingface.co/blog/ibm-research/altk-evolve-hmm)** Why agent memory should be calibrated to the model instead of simply increased. - **2026-08-11** · Article — **[Thinking of ACE? We Can Do It with Fewer Tokens](https://huggingface.co/blog/ibm-research/altk-evolve-sldd)** Comparing Evolve's targeted guideline retrieval with ACE's playbook approach and token usage. - **2026-04-08** · Article — **[ALTK‑Evolve: On‑the‑Job Learning for AI Agents](https://huggingface.co/blog/ibm-research/altk-evolve)** An introduction to learning reusable guidance from agent trajectories. - **2026-04-07** · Announcement — **[IBM introduces ALTK Evolve](https://www.ibm.com/new/announcements/altk-evolve-on-the-job-learning-for-ai-agents)** Evolve is opened to builders creating agents that learn from experience. - **2026-03-11** · Paper — **[Trajectory-Informed Memory Generation for Self-Improving Agent Systems](https://arxiv.org/abs/2603.10600)** The research framework and evaluation underlying Evolve. <!-- END LATEST-UPDATES --> ## Quick Start (Lite) [IBM Bob →](https://agenttoolkit.github.io/altk-evolve/examples/hello_world/bob/) [Claude Code →](https://agenttoolkit.github.io/altk-evolve/examples/hello_world/claude) [Codex →](https://agenttoolkit.github.io/altk-evolve/examples/hello_world/codex/) [Hermes →](https://agenttoolkit.github.io/altk-evolve/integrations/hermes/) ## Quick Start (Evolve MCP Server) ### Installation Prerequisites: - Python 3.12 or higher - `uv` (recommended) or `pip` From Source ```bash # Clone the repository and install dependencies git clone https://github.com/agenttoolkit/altk-evolve.git cd altk-evolve uv venv --python=3.12 && source .venv/bin/activate uv sync # Build the UI cd frontend/ui npm ci && npm run build cd ../.. ``` From PyPI ```bash pip install altk-evolve ``` **Optional Backend Dependencies:** The default filesystem backend uses simple text matching and requires no additional dependencies. For semantic vector similarity search, install one of these backends: For PostgreSQL with pgvector support (recommended for production): ```bash uv sync --extra pgvector ``` For Milvus support (optimized for large-scale vector search): ```bash uv sync --extra milvus ``` See the [Backend Configuration Guide](docs/guides/backend-configuration.md) for detailed comparison and setup instructions. ### Configuration For direct OpenAI usage: ```bash export OPENAI_API_KEY=sk-... ``` For LiteLLM proxy usage and model selection (including global fallback via `EVOLVE_MODEL_NAME`), see [the configuration guide](docs/guides/configuration.md). ### Running Services Start the Web UI and MCP server ```bash uv run evolve-mcp ``` The Web UI can be accessed from: `http://127.0.0.1:8000/ui/` ### Starting the Web UI and MCP Server If you only want to access the Web UI and API (without the MCP server stdio blocking the terminal), you can run the FastAPI application directly using `uvicorn`: ```bash uv run uvicorn altk_evolve.frontend.mcp.mcp_server:app --host 127.0.0.1 --port 8000 ``` Then navigate to `http://127.0.0.1:8000/ui/`. ### Starting only the MCP Server If you're attaching Evolve to an MCP client that requires a direct command (like Claude Desktop): ```bash uv run evolve-mcp ``` Or for SSE transport: ```bash uv run evolve-mcp --transport sse --port 8201 ``` Verify it's running: ```bash npx @modelcontextprotocol/inspector@latest http://127.0.0.1:8201/sse --cli --method tools/list ``` **Available tools:** - `get_entities(task: str, entity_type: str = "guideline", include_public: bool = False)`: Get relevant entities for a specific task. Set `include_public=True` to merge in public entities from all other namespaces; those results are annotated with `[public: {owner_id}]`. - `get_guidelines(task: str)`: Get relevant guidelines for a specific task (backward compatibility alias for `get_entities`). - `get_guidelines_with_attribution(task: str)`: Return formatted guidelines with the entity IDs used to build the prompt. - `get_relevant_guidelines(task: str, top_k: int | None, core_support: int | None)`: Retrieve the always-on guideline core plus a task-relevant dosage. - `list_entities(...)`: Return structured, filtered, cursor-paginated entity inventory for user and administrative UIs. - `get_entity(entity_id: str, user_id: str | None, record_access: bool = True)`: Return one structured entity, enforcing ownership when a caller ID is supplied. - `patch_entity_metadata(entity_id: str, metadata_patch: str, user_id: str | None)`: Merge JSON metadata through the memory hook seam. - `record_access(entity_ids: list[str], accessed_at: str | None)`: Explicitly stamp the retention engine's `last_accessed` signal. - `validate_retention_policy(policy: str)`: Validate and normalize a JSON retention policy without scanning data. - `put_retention_policy(policy_id: str, name: str, policy: str, ...)`: Create or replace an Evolve-owned retention policy. - `get_retention_policy(policy_id: str)` / `list_retention_policies()`: Read the namespace's policy catalog for operators and management UIs. - `run_retention(policy_id: str, dry_run: bool = True, ...)`: Dry-run or apply a stored policy and persist a structured, entity-linked report. - `list_retention_runs(...)`: Read namespace-scoped retention run history, optionally filtered by agent or policy. - `get_compliance_status()`: Report backend health, retention availability, hook coverage, and configured plugin health. - `save_trajectory(trajectory_data: str, task_id: str | None, owner_id: str | None)`: Save a conversation trajectory and generate new guidelines. - `create_entity(content: str, entity_type: str, metadata: str | None, enable_conflict_resolution: bool, owner_id: str | None, visibility: str = "private")`: Create a single entity. Pass `visibility="public"` and `owner_id` to make it immediately discoverable by other namespaces. - `publish_entity(entity_id: str, user_id: str | None)`: Make an entity publicly visible to all namespaces. Records the caller as owner and stamps `published_at`. - `unpublish_entity(entity_id: str, user_id: str | None = None)`: Revert an entity to private visibility. Ownership is enforced server-side: if the entity has an `owner_id`, `user_id` must match it. - `delete_entity(entity_id: str)`: Delete a specific entity by its ID. ### Filter Migration Note Entity search filters reserve bare keys for top-level schema columns only: `id`, `type`, `content`, and `created_at`. If you need to filter on JSON metadata, use the `metadata.<key>` form. For example, use `filters={"type": "trajectory", "metadata.task_id": "123"}` instead of `filters={"type": "trajectory", "task_id": "123"}`. Existing integrations that stored custom fields in entity metadata should update filter writers to add the `metadata.` prefix for those keys. ## Features - **Proactive**: Learns how to recognize problems and their solutions, and generates guidelines that get automatically applied to new tasks. - **Conflict Resolution**: Update existing guidelines when new information contradicts them. - **On Command**: An array of tools to manage guidelines whether in the agent or through a CLI - **Sharing**: Publish individual entities so other agents can discover and retrieve them across namespaces. ## Architecture Evolve is built on a modular architecture which forms a feedback loop, taking conversation traces (trajectories) from an agent, extracting key insights into a database, feeding it back into the agent. _Lite Mode omits the Interaction layer. All activity is performed in-agent_ <picture> <source media="(prefers-color-scheme: dark)" srcset="docs/assets/architecture-wide-dark.svg"> <img src="docs/assets/architecture-wide-light.svg" alt="Architecture" width="480"> </picture> ## Entity Sharing Evolve supports sharing entities across namespaces using a simple public/private visibility model. **Visibility** is stored in each entity's metadata and is private by default. Existing entities without a `visibility` field are unaffected. | Metadata field | Description | |---|---| | `owner_id` | User ID who created or last published the entity | | `visibility` | `"private"` (default) or `"public"` | | `published_at` | ISO-8601 timestamp of the most recent publish | ### MCP Tools **Personal facts on a shared Evolve service:** ```python store_user_facts(namespace_id="service-instance-1", user_id="alice", message="I prefer concise answers") retrieve_user_facts(namespace_id="service-instance-1", user_id="alice", query="answer preferences") ``` Pass the service instance ID as `namespace_id` and the individual user's ID as `user_id` on both calls. Explicitly scoped retrieval filters by that exact pair, including query fallback, and never falls back to another user's facts. Empty explicit namespaces or user IDs are rejected. Calls omitting `namespace_id` retain the configured default namespace and legacy default-user fallback. Integrating clients must supply the scope; upgrading Evolve alone cannot infer which service instance an unscoped request belongs to. **Publishing an entity:** ```python publish_entity(entity_id="42", user_id="alice") ``` Sets `visibility=public` and records the owner and publish timestamp. **Unpublishing:** ```python unpublish_entity(entity_id="42", user_id="alice") ``` Reverts the entity to private. The entity stays in its namespace — only its visibility changes. **Retrieving public entities from all namespaces:** ```python get_entities(task="write safer code", include_public=True) ``` Merges results from the caller's namespace with public entities from all other namespaces. Public results are annotated with `[public: {owner_id}]`. **Creating an entity with visibility:** ```python create_entity(content="...", entity_type="guideline", visibility="public", owner_id="alice") ``` ### What's deferred (Phase 1C) REST API endpoints (`GET /api/entities/public`, publish/unpublish routes) and UI controls are not yet implemented. ## Guideline Provenance Evolve automatically tracks the origin of every guideline it generates or stores. Every guideline entity contains `metadata` identifying its source: - `creation_mode`: Identifies how the guideline was created (`auto-phoenix` via trace observability, `auto-mcp` via trajectory saving tools, or `manual`). - `source_task_id`: The ID of the original trace or task that inspired the guideline, providing full auditability. See the [Low-Code Tracing Guide](docs/guides/low-code-tracing.md#6-understanding-guideline-provenance-metadata) for more details. ## Contributing, Community, and Feedback Evolve is an active project, and real‑world usage helps guide its direction. If you’re experimenting with Evolve or exploring on‑the‑job learning for agents, feel free to open an issue or discussion to share use cases, ideas, or feedback. See the [Contributing Guide](CONTRIBUTING.md) to understand our development process, or how to submit changes, report bugs, or propose features. ### Embedded memory API and scheduling Hosts can mount the [scoped REST router](docs/guides/embedded-memory-api.md) with their own client and authentication dependencies. Evolve owns [retention schedules and worker execution](docs/guides/retention-scheduling.md), using Kubernetes-compatible cron, timezone, concurrency, deadline, and suspension fields. Use `evolve retention schedules` to manage schedules and `start`/`stop` to enable or suspend them. The Evolve service owns background execution. The [public retention service](docs/guides/retention-api.md) is available as `client.retention(namespace_id, agent_id=...)`; CLI, REST, MCP, and scheduling share its operations and scope checks.